KR20170076895A - Method for digital image judging and system tereof, application system, and authentication system thereof - Google Patents

Abstract

A digital image determination system and method are disclosed. According to one aspect of the present invention, a digital image determination system acquires a plurality of digital images including a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state on the same object And a control module for determining whether the plurality of digital images have photographed a three-dimensional object or a two-dimensional image based on the plurality of digital images acquired by the acquisition module, Wherein the control module analyzes the first digital image and the second digital image and determines whether the digital images have taken a three-dimensional object or a two-dimensional image based on the analysis result .

Description

TECHNICAL FIELD [0001] The present invention relates to a digital image judging system, an image processing method,

The present invention relates to a system and method for analyzing a digital image and determining whether a digital image is an image of a real object or an image of an image of the object.

Recently, online services such as online commerce have been widely used. It is very important for an online service to make sure that a user is a legitimate user or a trusted party.

In the case of online or non-face-to-face authentication, face-to-face authentication or non-face-to-face authentication technology has been introduced in which a facial photograph or identification card or other authentication means is scanned or photographed and transmitted online to a certification authority, .

However, the present non-face authentication technology has a problem that a photograph can be abused or forged by a hacker or the like and can be abused. In addition, there are cases where a car insurance company provides a service for checking mileage or black box installation and discounting insurance premiums. At this time, there are cases where forged pictures are transmitted, Even if you do not have it, you can steal photos of others and pretend to pretend that you own the item.

Therefore, if a digital image can distinguish whether a three-dimensional object is captured or a two-dimensional image is captured, it can be used for various online authentication and services, and a technical idea is required.

Korean Unexamined Patent Application Publication No. 10-2005-0009415, "Mutual authentication method using image image and computer readable recording medium recording program for executing this method"

SUMMARY OF THE INVENTION The present invention provides a method and system for determining whether a digital image is a real object or a two-dimensional image, .

According to an aspect of the present invention, an image determination system is provided for obtaining a plurality of digital images including a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state, And a control module for determining whether the plurality of digital images have taken a three-dimensional object or a two-dimensional image based on the plurality of digital images acquired by the acquisition module Wherein the control module analyzes the first digital image and the second digital image and determines whether the digital images are three-dimensional real objects or two-dimensional images based on the analysis result .

Wherein the first digital image and the second digital image are respectively in a state in which the digital image judging system is installed or a lighting device in an image photographing apparatus in which communication with the digital image judging system is in an inactivated state and in an activated state, .

Wherein the control module is operable to detect from the first digital image all of the first digital image or a first edge image that has detected an edge in a predetermined predetermined area and a second edge image from the second digital image, An edge detection module for generating a second edge image that has detected an edge in the particular area of the image and an edge detection module for analyzing edges of each of the first edge image and the second edge image generated by the edge detection module, A determination module for determining whether a three-dimensional object object is photographed or a two-dimensional image is photographed.

Wherein the determining module compares at least one of the first edge image and the intensity of the edge or the edge included in the second edge image and determines whether the digital images have photographed the physical object based on the comparison result can do.

Wherein the determination module determines the number of first target shapes and the number of second targets that are detected from the first analysis image and the second analysis image corresponding to each of the first edge image and the second edge image, It is possible to determine whether the digital images have taken a real object based on the number of shapes.

Wherein the control module extracts contours of each of the edges included in each of the first analysis image and the second analysis image and extracts contours of the first target shape number and the second target shape And a detection module for calculating the number of the plurality of sensors.

Wherein the first analysis image and the second analysis image are images obtained by blurring the first edge image and the second edge image at least once to a predetermined level or the first edge image and the second edge image, And the size of the 2 < nd > edge image is reduced at least once to a predetermined level.

Wherein the image capturing apparatus is configured to transmit the first digital image in a state in which the illuminator is inactivated and the second digital image in a state in which the illuminator is in an activated state, And the digital image is continuously photographed.

According to an aspect of the present invention, there is provided a data processing system including a storage medium storing a program and a processor for executing the program, the processor executing the program, 1 digital image and a second digital image photographed in the second illumination state, and judges whether the digital images have photographed the three-dimensional object or the two-dimensional image based on the analysis result have.

According to an aspect of the present invention, there is provided an application system installed in an image photographing apparatus, including an interface module for receiving a photographing request signal from a user, a control unit for controlling an illumination device provided in the image photographing apparatus, Wherein the control module controls the first digital image in the first illumination state and the second digital image in the second illumination state to continuously photograph a predetermined object in response to the photographing request signal.

Wherein the first digital image and the second digital image are analyzed by a predetermined digital image determination system to determine whether the first digital image and the second digital image are images of a three- It can be judged whether or not it is.

According to another aspect of the present invention, there is provided a digital image determination method for a digital image determination system, the digital image determination system comprising: a plurality of digital images, each of which includes a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state, Analyzing the acquired first digital image and the second digital image, and determining whether the plurality of digital images have photographed the three-dimensional physical object based on the analysis result, And determining whether or not it is a one-time operation.

Analyzing the acquired first digital image and the second digital image, and determining whether the plurality of digital images are photographed of a three-dimensional object or a two-dimensional image based on an analysis result From the first digital image, a first edge image that detects an edge in all or a predetermined specific area of the first digital image, and a second edge image that detects an edge in all or a predetermined predetermined area of the second digital image And a second edge image obtained by analyzing the edge of each of the generated first edge image and the second edge image so as to determine whether the digital images have photographed the three- And determining whether the image is photographed or not.

Wherein the step of analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images have taken a three-dimensional real object or a two-dimensional image, Comparing at least one of the edge image and the intensity of the edge or the edge included in the second edge image and determining whether the digital images have photographed the physical object based on the comparison result .

Wherein the step of analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images have taken a three-dimensional real object or a two-dimensional image, Based on the number of first target shapes and the number of second target shapes, which means the number of the predetermined target shapes detected from each of the first analysis image and the second analysis image corresponding to each of the first edge image and the second edge image, And determining whether the digital images have taken a physical object.

Wherein the step of analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images have taken a three-dimensional real object or a two-dimensional image, Extracting the contours of each of the edges included in the analysis image and the second analysis image and calculating the first target shape number and the second target shape number based on the extracted contours .

Wherein the first analysis image and the second analysis image are images obtained by blurring the first edge image and the second edge image at least once to a predetermined level or the first edge image and the second edge image, And the size of the 2 < nd > edge image is reduced at least once to a predetermined level.

According to an aspect of the present invention, there is provided a method of an image shooting apparatus, the method comprising: receiving a shooting request signal from a user; And successively photographing the digital image and the second digital image in the second illumination state.

Wherein the application execution method further comprises the step of transmitting the first digital image and the second digital image to a predetermined digital image determination system, wherein the first digital image and the second digital image are analyzed by the digital image determination system, It can be judged whether the digital image is a three-dimensional object or a two-dimensional image.

According to another aspect of the present invention, there is provided a computer program installed in a data processing apparatus and stored in a recording medium for performing the above-described method.

According to the present invention, an object to be photographed is photographed with a different activation state of the lighting apparatus, whereby the object to be photographed can be a two-dimensional image or a three-dimensional object There is an effect that it can be easily discriminated.

BRIEF DESCRIPTION OF THE DRAWINGS A brief description of each drawing is provided to more fully understand the drawings recited in the description of the invention.
FIG. 1 is a diagram for explaining a schematic system configuration for a digital image determination method according to an embodiment of the present invention.
2 is a block diagram illustrating a schematic configuration of a digital image determination system according to an embodiment of the present invention.
3 is a block diagram illustrating a schematic configuration of a data processing system in which a digital image determination system according to an embodiment of the present invention is installed.
4 is a block diagram illustrating a schematic configuration of an application system according to an embodiment of the present invention.
5 is a view for explaining an example of determining whether a plurality of images are images taken of a physical object according to a digital image determination method according to an embodiment of the present invention.
6 is a diagram for explaining an example of detecting a target object according to a digital image determination method according to an embodiment of the present invention.
FIGS. 7 to 12 are views for explaining an example of determining whether a plurality of images are images taken of a physical object according to a digital image determination method according to another embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise.

In this specification, terms such as "comprise," "comprising," and the like are intended to specify that there are stated features, numbers, steps, operations, elements, parts or combinations thereof, But do not preclude the presence or addition of one or more other features, steps, operations, elements, components, or combinations thereof.

Also, in this specification, when any one element 'transmits' data to another element, the element may transmit the data directly to the other element, or may be transmitted through at least one other element And may transmit the data to the other component. Conversely, when one element 'directly transmits' data to another element, it means that the data is transmitted to the other element without passing through another element in the element.

Hereinafter, the present invention will be described in detail with reference to the embodiments of the present invention with reference to the accompanying drawings. Like reference symbols in the drawings denote like elements.

FIG. 1 is a diagram for explaining a schematic system configuration for a digital image determination method according to an embodiment of the present invention.

 Referring to FIG. 1, a digital image determination system (hereinafter, 'determination system', 100 or 100-1) may be provided to implement a digital image determination method according to an embodiment of the present invention.

According to the technical idea of the present invention, the determination system 100 or 100-1 may use the plurality of images photographed for the same object to determine whether the plurality of images are images of a three- Or a system for judging whether images are photographed images.

The judgment systems 100 and 100-1 may be installed in predetermined data processing systems 10 and 20 to implement the technical idea of the present invention. For example, the determination systems 100 and 100-1 may be installed in the client 10 or may be installed in the server 20 and implemented. According to an embodiment of the present invention, the judgment system 100 or 100-1 may be distributed in the client 10 and the server 20 and may be implemented by organically combining the distributed configurations through wired / .

The judgment system 100 or 100-1 means a system in which predetermined software for implementing the technical idea of the present invention and hardware of the data processing system 10 and 20 in which the software is installed are combined and implemented .

The client 10 may be a data processing system possessed by a user such as a portable terminal, a computer, a notebook computer, a digital camera, or the like, and may be any type of data processing system having data processing capability for realizing the technical idea of the present invention It can mean. For example, the client 10 may include an image capturing sensor (e.g., a camera sensor) for capturing a predetermined object. However, when the determination system 100-1 is provided to the client 10, the client 10 may receive the plurality of images according to the technical idea of the present invention from the outside without directly shooting In this case, it is needless to say that the client 10 may perform the function of the server. Of course, the judgment system 100-1 provided in the client 10 may judge whether or not the real object has been photographed with respect to a plurality of images photographed by the client 10.

The server 20 may perform a function of determining whether or not a plurality of images received from the client 10 have been photographed by the client 10 while communicating with the client 10. In this case, the client 10 may take a plurality of images and transmit the images to the server 20. Then, the judgment system 100 provided in the server 20 can judge whether the plurality of images transferred are photographed of a real object or a two-dimensional image. The server 20 can directly provide a predetermined service to the client 10 or control a predetermined service system (not shown) to provide the service to the client 10 according to the determination result.

Hereinafter, for convenience of explanation, the client 10 photographs a plurality of images, and the judgment system 100 provided in the server 20 detects a plurality of images received from the client 10, It is to be understood that the scope of the present invention is not limited thereto.

The judgment system 100 provided in the server 20 receives a plurality of digital images from the client 10 and photographs the three-dimensional physical objects (for example, a user's face or an actual article) (Hereinafter referred to as " physical object photographing authentication "). According to the technical idea of the present invention, when the photographed object is an object (for example, an ID card or the like) capable of authenticating the principal, it can be an effective personal authentication method. If the object of photography is a target object, It can be used to confirm the credibility of the counterparty.

The server 20 may receive the digital images directly from the client 10 and send the digital images to a predetermined external system (e.g., a social network system, an image publishing service providing system, etc.) When the digital images are uploaded, the digital image may be received from the external system. Alternatively, after the digital image photographed from the client 10 is transmitted to a predetermined other terminal (e.g., a user's computer or the like), the other terminal may transmit the digital image to the server 20. In the present invention, a method of receiving a digital image by the server 20 may be variously performed in association with the client 10. [

In the present invention, a plurality of digital images include a first digital image and a second digital image that have captured the same object in different illumination states. For example, the first digital image may be an image of an object in a state in which an illumination device (for example, a flash) provided in the image capturing apparatus 10 that has captured the first digital image is inactivated. The second digital image may be an image of the object while the image capturing apparatus 10 activates the illuminating apparatus.

According to an example, the first digital image and the second digital image may have the same shooting condition (e.g., an external light source, a shooting angle, etc.) other than an illumination condition (illumination condition). Therefore, the image capturing apparatus 10 can continuously photograph the first digital image and the second digital image. To this end, the image photographing apparatus 10 may be provided with a predetermined application for implementing the technical idea of the present invention. The image photographing apparatus can continuously photograph the first digital image and the second digital image even when the user performs only one photographing request (for example, selection of a specific UI) through the application. The application may also deactivate the illumination device when the first digital image is taken and control the illumination device to be activated when the second digital image is taken. The application system will be described later.

The plurality of digital images may include at least the first digital image and the second digital image, respectively. The digital images may include a plurality of first digital images and a plurality of second digital images. However, in the present invention, for convenience of explanation, the first digital image and the second digital image may be included one by one I will explain.

Although the object to be photographed in the present specification is an example of a financial transaction card, the object may be an ID card or other object expected to be occupied by the user, A face, etc.), a real object such as an actual article, and the like.

The present invention can be used for various services depending on what the object is, such as non-face-to-face authentication or settlement. If desired, the server 20 may further authenticate whether the digital images have been taken by the client 10 of the user's name. For example, it is possible to selectively provide a service by additionally performing authentication of whether the digital images are photographed with a physical object or by performing another predetermined authentication (for example, authentication through a mobile phone authentication, a passbook or other transaction means, ARS authentication, etc.).

The configuration of the judgment system 100, 100-1 for realizing such a technical idea will be described with reference to Fig. 2 is a block diagram illustrating a schematic configuration of a digital image determination system according to an embodiment of the present invention.

As shown in FIG. 2, the determination system 100, 100-1 may include a control module 110 and an acquisition module 120. [ The control module 110 may include an edge detection module 111, a determination module 112, and / or a detection module 113. In accordance with an embodiment of the present invention, some of the components may not be essential components in the implementation of the present invention, and in accordance with an embodiment, the determination system 100, It goes without saying that many components may be included.

The judgment system 100 or 100-1 may include a hardware resource and / or software necessary for implementing the technical idea of the present invention, and it may mean one physical component or one device It does not mean anything. That is, the judgment systems 100 and 100-1 may mean a logical combination of hardware and / or software provided to implement the technical idea of the present invention. If necessary, The present invention may be embodied as a set of logical structures for realizing the technical idea of the present invention. In addition, the judgment system 100 or 100-1 may mean a set of configurations separately implemented for each function or role for implementing the technical idea of the present invention. For example, the control module 110 and the acquisition module 120 may be located in different physical devices, or may be located in the same physical device. Also, depending on the implementation, the combination of software and / or hardware that constitute each of the control module 110 and / or the acquisition module 120 may also be located in different physical devices, To implement each of the above modules.

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the module may refer to a logical unit of a predetermined code and a hardware resource for executing the predetermined code, and it does not necessarily mean a physically connected code or a kind of hardware But can be easily deduced to the average expert in the field of the present invention.

The control module 110 may control the other components included in the determination system 100 or 100-1 such as the acquisition module 120, the edge detection module 111, the determination module 112, and / Detection module 113, etc.) and / or resources.

The acquisition module 120 may acquire a plurality of digital images to be used for a physical object imaging authentication. The plurality of digital images include at least a first digital image and a second digital image.

Embodiments in which the acquisition module 120 obtains the digital images photographed for the same object may vary. For example, if the determination system 100 is included in the server 20, the acquisition module 120 may acquire the digital images from the client 10. Or if the determination system 100-1 is included in the client 10, the acquisition module 120 may acquire the captured digital images when the client 10 photographs the digital images . Various other embodiments may be possible.

The technical idea of the present invention is that the reflection characteristics of illumination in a real object and the reflection characteristics of illumination in a two-dimensional image are different from each other, and a first digital image and a second digital image, Can be used. Accordingly, various embodiments are possible as long as the first illumination state and the second illumination state can exhibit such a degree that the reflection characteristic can be derived well.

According to an embodiment of the present invention, the first illumination state is a state in which the flash of the image capturing apparatus 10 is inactivated (or off), and the second illumination state is a state in which the flash of the image capturing apparatus 10 is activated Lt; / RTI > But it goes without saying that the present invention may be practiced differently depending on the function of the illumination device provided in the image photographing apparatus 10 according to the embodiment. For example, both the first illumination state and the second illumination state may be a state in which the color, intensity, and the like of the illumination are changed in a state in which the illumination apparatus is activated.

When the digital images, i.e., the first digital image and the second digital image, are acquired by the acquisition module 120, the control module 110 analyzes the digital images to generate a physical object photographing authentication Can be performed.

The control module 110 may be configured such that, when the physical object is photographed, when the image characteristic acquired through each of the first digital image and the second digital image and the two-dimensional image are captured, the first digital image and the second digital image The image characteristics obtained through each of them may be different from each other, and the real object photographing authentication can be performed using the same.

According to an example, the control module 110 may detect an edge from a first digital image and a second digital image. The method of detecting the edge may be various. Edge detection algorithms that are well known in the field of image processing, such as, for example, Canny Edge algorithm, can be used to detect the edges of the first digital image and the second digital image. This edge detection can be performed by the edge detection module 111. [

The fact that the edge detection module 111 detects an edge from a first digital image or a second digital image means that an edge is directly detected from the first digital image obtained by the acquisition module 120 or from the second digital image itself But may also include the case of performing predetermined pre-processing on the first digital and / or the second digital image as well as detecting an edge from pre-processed images . The preprocessing may include detecting an area corresponding to the object (e.g., a card) in the first digital and / or the second digital image and warping or resizing the area. This may be due to the fact that the projection ray of the camera is not easy to be orthogonal to the front of the object, even if the user tries to shoot the frontal view of the object as much as possible. Also, even if the first digital image and the second digital image are continuously photographed, there may exist shaking or the like, and therefore, a process of resizing them to the same or similar size may be necessary.

In order to simplify the preprocessing process, the application provided in the image photographing apparatus 10 provides a predetermined reference line on the camera frame image, and when the user places the object in the aligned state (or in the aligned state) As shown in FIG.

The edge detection module 111 may detect an edge for all of the first digital image but may detect an edge for only a part of the first digital image (hereinafter, 'object area'). Further, depending on the embodiment, the edge may be detected only in a specific region predetermined in the object region (for example, a region in which the IC chip of the card exists or a region in which a specific character (e.g., a number) exists). The specific region may be a region in which differences in image characteristics (for example, reflection characteristics of illumination) occur as much as possible when an image of a real object and a two-dimensional image (hereinafter, referred to as an & have. This area may be, for example, an area where there are three-dimensional bends or requests, or an area painted with another material, and may vary according to other implementations. Therefore, the edge detection module 111 may detect an edge with respect to an object area, or may detect an edge only with respect to a specific area in an object area. Of course, the area for detecting the edge in the first digital image and the area for detecting the edge in the second digital image can be set to be the same. In the present specification, the shape of an edge detected from the first digital image by the edge detection module 111 is referred to as a first edge image, and the shape of an edge detected from the second digital image is referred to as a second edge image.

According to the technical idea of the present invention, the object object photographing authentication can be performed using the edge image corresponding to the first digital image and the second digital image. In a real object and an image-taking image, a region where a change in image characteristic is relatively large depending on a change in an illumination state may be an area corresponding to an edge. In the image of the real object, the region represented by the edge may be a region in which there are strong irregularities or bends, a region in which the shape or color is mutually changed even if there are no irregularities or bends, have.

For example, in a region where the concavities and convexities are strongly present, the intensity of the edge may vary greatly depending on the illumination state of the photographed image. For example, a particular region in which the ruggedness exists in the physical object may have the edge detected relatively weakly in the first digital image, while the edge may be detected relatively weakly in the second digital image. That is, since the difference in the reflection characteristic of the illumination is relatively large in the irregular portion, stronger edges (i.e., a large difference in pixel value) can be detected as the illumination is strong at the time of image taking.

In addition, the region having different materials even if the object is not irregular or uneven can be a region where a stronger edge is detected as the illumination is stronger.

In the case of an image-taking image, there is no difference in color or in the same material, so there is no irregularity or material difference. In such a case, as the illumination becomes stronger, There may be a tendency to disappear.

Therefore, according to the technical idea of the present invention, there is a change characteristic of an edge in which an amount or an intensity of an edge to be detected changes according to a change of an illumination state, and a change in an edge when a real object is photographed, It is possible to perform the object object photographing authentication using the fact that the characteristics are different.

Accordingly, the determination module 112 can perform the object object photographing authentication by analyzing the first edge image and the second edge image. The determination module 112 may compare at least one of the amount or the intensity of the edge included in the first edge image and the edge included in the second edge image and determine whether the object is photographed based on the comparison result . The amount of edge may mean the length and / or area of the entire edge included in each edge image. The intensity of an edge can be a measure of the difference between the pixel value of the edge portion and the pixel value around the edge.

The edge appears in a region where there are irregularities or a region where a shape or color difference exists as well as a region where a material changes, and in an area where there is a difference in shape or color, the edge is detected in the second illumination state rather than in the first illumination state The edge may be smaller or the edge may be weaker in strength. Therefore, when judging whether the object is a real object or not by using the amount or strength of the edge, it is preferable to detect the first edge image and the second edge image from a predetermined area, such as a part where irregularities exist or a material changes in the object area It is possible. In this case, in the physical object, the amount or intensity of the edge detected in the second edge image may be greater or more intense than the amount or intensity of the edge detected in the first edge image. However, There may be a characteristic in which the amount or intensity of edges to be detected is reduced or weakened.

Therefore, the determination module 112 may determine the digital images as images of the physical object when the amount or intensity of the edges included in the second edge image is larger or larger than the first edge image. Conversely, if the amount or intensity of an edge detected from the second edge image is smaller or smaller than that of the first edge image, the digital images may be determined as an image taken image.

According to the technical idea of the present invention, the determination module 112 may determine uncertainties (for example, due to other external factors) that may occur when determining whether the object is a real object according to a change characteristic of an edge The amount of edge or the degree of strength that can be authenticated as a physical object, etc.) when the change characteristics of the edge are displayed.

According to an embodiment of the present invention, the determination module 112 performs a physical object imaging authentication based on a clearer and more quantitative criterion than the change in the amount or intensity of edge detected from the first edge image and the second edge image You may.

This criterion may be, for example, a method of performing the object object photographing authentication according to the number of detected target shapes from the first edge image and the second edge image, respectively. The target shape may refer to a type (e.g., a number, a character, etc.) of the target shape detected by the control module 110, and may be a shape of a target or a target that can be recognized using edge information. The determination module 112 determines how many first target shapes are detected from the first analysis image corresponding to the first edge image and a second target shape that is detected from the second analysis image corresponding to the second edge image The object object photographing authentication can be performed based on the number of persons.

The target shape may be, for example, a shape of a target that is displayed on the object and is expressed by an uneven portion of the object or a different material. The case where the target shape is a number corresponding to the card number displayed on the card will be described as an example.

The determination module 112 may perform the object object photographing authentication based on the number of each of the numbers detected from the first analysis image and the second analysis image. The target shape may vary not only with such numbers, but also with objects such as Korean alphabet and alphabet.

The first analysis image and the second analysis image may be the first edge image and the second edge image respectively, or the first edge image and the second edge image may be images processed in a predetermined manner.

For example, the first analysis image and / or the second analysis image may be a blurred image of the first edge image and / or the second edge image to a predetermined level, or the image may be a downsized image. If the image processing is to be performed, for example, the intensity of the edge of the first edge image and the edge image of the second edge is large, so that the same target shape number can be detected from the first edge image and the second edge image .

For example, the object may be a card and the target shape may be a number displayed on the card. If the number of target shapes detected from the second edge image is larger than the number of target shapes detected from the first edge image, the determination module 112 may determine that the digital images are photographed of the physical object. However, each of the 16 numbers may be detected from the first edge image and the second edge image. In such a case, it may not be possible to perform the object object photographing authentication by comparing the number of the target shapes. For this, the control module 110 may blur the first edge image and the second edge image to a certain level or reduce the size of the second edge image. That is, the image process for lowering the intensity of the edge to a certain level can be performed. The result of the execution of the image process may be the first analysis image and the second analysis image.

Then, the determination module 112 may compare the number of target shapes detected from the first analysis image and the second analysis image to perform the object object photographing authentication. If all the target shapes are detected even when the target shape is detected from the first analysis image and the second analysis image, the image process of lowering the strength of the edge is performed again. When there is a difference in the number of detected target shapes The blur processing or the downsizing can be performed at a predetermined level.

As a result, the determination module 112 can determine whether the digital images are a physical object image or an image pickup image based on the difference in the number of target shapes detected from the first analysis image and the second analysis image . When the digital images have captured a real object, the edge of the second analysis image becomes stronger and more target shapes are detected, so that when more target shapes are detected from the second analysis image, the determination module 112 It can be judged that the digital images are photographed on the physical object. Conversely, if more target shapes are detected from the first analysis image, or if no target shape is detected from both the first analysis image and the second analysis image, the digital images can be judged as the image taken image.

The detection module 113 may perform a function of detecting a target shape from each of the first analysis image and the second analysis image. The detection module 113 can detect a target shape to be detected from the first analysis image and the second analysis image in various ways.

According to an example, the detection module 113 may extract a contour of edges included in each of the first analysis image and the second analysis image. A contour can mean the outline of the edges. And the detection module 113 may detect the target shape based on each of the contours.

The method of detecting the target shape using the extracted contour may vary. For example, the target shape may be detected using optical character recognition. Since various techniques used for optical character recognition are known, a detailed description thereof will be omitted in the present invention. In addition, the target shape may be detected using a template provided by a predetermined OS (e.g., Windows?).

Alternatively, the target shape may be detected using a minimum bounding box as in the technical concept of the present invention. The detection module 113 may set a minimum bounding box in each of the extracted contours. Based on the size of the minimum bounding box, it can be determined whether or not the edge corresponding to the contour included in the minimum bounding box is the target shape. For example, if the minimum bounding box corresponding to a particular contour is equal to or within a predetermined error range of a reference bounding box of a predetermined target shape, the minimum bounding box may be determined as a minimum bounding box of the target shape. Thus, the number of the minimum bounding boxes having a size equal to or greater than a size of the reference bounding box may be the number of target shapes to be detected. This will be described later with reference to Fig.

According to the technical idea of the present invention, the detection module 113 can calculate the number of target shapes detected from each of the first analysis image and the second analysis image, and the determination module 112 can calculate the number of target shapes detected from the first analysis image and the second analysis image, And can perform physical object photographing authentication of digital images based on the number of target shapes detected from the analysis image. Figs. 5 and 7 to 10 are diagrams for explaining the results of experiments. When a physical object (for example, an actual card) is photographed, a target shape detected from the second analysis image ) Is larger than the number of target shapes detected from the first analysis image. In the case of an image-captured image, no target shape was detected from both the first analysis image and the second analysis image. Depending on the implementation, the number of target shapes detected from the second analysis image may be less than the number of target shapes detected from the first analysis image.

3 is a block diagram illustrating a schematic configuration of a data processing system in which a digital image determination system according to an embodiment of the present invention is installed.

Referring to FIG. 3, the data processing system 30 may be a system having the determination system 100 or 100-1. The data processing system 30 may include a storage medium 32 in which the software (or program) for implementing the determination system 100, 100-1 is stored and a processor 31 for executing the software have. The processor 31 may execute the program stored in the storage medium 32 and perform functions performed by the judgment system 100 or 100-1 as described above.

The data processing system 30 may be, for example, a client 10 or a server 20. According to an embodiment of the data processing system 30, the data processing system 30 may include various peripherals 33. According to an example, the peripheral device may be, but is not limited to, an image capturing sensor, a lighting device, and the like.

Meanwhile, in order to implement the technical idea of the present invention, the client 10 may be provided with a predetermined application system. 4 is a block diagram illustrating a schematic configuration of an application system according to an embodiment of the present invention.

Referring to FIG. 4, the application system 40 may include a control module 41 and an interface module 42. The application system 40 may be implemented by organically combining software (application or program) for performing the functions of the application system 40 and hardware of an image photographing apparatus (not shown) installed with the software. The image photographing apparatus may be, for example, a client 10.

The image photographing device (not shown) may be provided with an illumination device (e.g., a flash) and an image photographing sensor for photographing an image.

The control module 41 may control the illumination device and / or the image pickup sensor. The interface module 42 may receive a photographing request signal from a user. Then, in response to the photographing request signal, the control module 41 controls the illumination device 40 to sequentially photograph the first digital image in the first illumination state and the second digital image in the second illumination state, And the image pickup sensor. The first illumination state may be a state in which the illumination device is deactivated, and the second illumination state may be in an activated state, but various other embodiments may be possible.

In addition, even when a photographing request signal (selection of a specific button or a UI) is inputted from the user through the interface module 42, the control module 41 can continuously output the first digital image and the second digital image . To continuously photograph means to photograph at least two images successively in a relatively short time. Of course, the action to be performed by the user for continuous shooting may be an input of one shot request signal, but various embodiments may be possible. For example, in the case of performing an image capturing manually (for example, when a specific button or UI is selected) by the user, the control module 41 photographs the first image without activating the illumination device, Can be photographed while the lighting apparatus is activated.

The photographing of the first image may be performed even if the user does not explicitly request the photographing. For example, the photographing of the first image may be performed automatically such that the user does not perceive the photographing. Therefore, even if the user performs only one act of photographing, the control module 41 photographs at least two images, one of which can be photographed without the lighting device being activated and the other can be photographed with the lighting device being activated have. The order of activation of the lighting device may vary depending on the implementation. In any case, the user may perceive that only one photographing has been performed with the lighting device activated.

Then, the photographed first digital image and the second digital image are transmitted to a server (for example, 20) so that the physical object photographing authentication can be performed by the judgment system 100 provided in the server (for example, 20). Alternatively, when the judgment system 100 or 100-1 is provided in the image photographing apparatus (not shown), the image photographing apparatus (not shown) may perform the object object photographing authentication itself. The image capturing apparatus may be any type of data processing apparatus that performs a function of capturing an image. For example, the image capturing apparatus may be a portable terminal, a digital camera, a notebook, a tablet, and the like, but is not limited thereto.

FIG. 5 is a diagram for explaining an example of determining whether images are images taken of a physical object according to a digital image determination method according to an embodiment of the present invention.

Referring to FIG. 5, the first digital image 50 and the second digital image 51 may be as shown in FIG. The acquisition module 120 of the judgment system 100 or 100-1 may receive the first digital image 50 and the second digital image 51 from the client 10. [ FIG. 5 shows a case where an experiment is performed in a state in which a part of an object is artificially masked.

The edge detection module 111 may then generate the first edge image 50-1 and the second edge image 51-1. 5 illustrates edge images 50-1 and 51-1 in which edges are extracted from an object area (for example, an area corresponding to a card) that is a part of each of the first digital image 50 and the second digital image 51 However, according to an embodiment, an edge image may be generated by extracting an edge only from a specific region (for example, an area in which an IC chip exists) 50-2 and 51-2 in the object region. Alternatively, an edge image may be generated by extracting an edge only from a specific region (for example, a region in which a card number is displayed, 50-3, 51-3) in the object region.

FIG. 5 shows a case in which a physical object is photographed. As can be seen by comparing the first edge image 50-1 and the second edge image 51-1, the irregular region (for example, The edge portion is detected more strongly in the second edge image 51-1 and the edge portion in accordance with the change of the shape (or color) in the plane is set such that the second edge image 51-1 is rather weak . Accordingly, the control module 110 can perform the object object photographing authentication of the digital images (e.g., 40, 41) using the change characteristic of the edge.

Further, the number in which the target shape (for example, a number corresponding to the card number) is detected as described above may be used. In the second edge image 51-1 shown in Fig. 5, a minimum bounding box is displayed in each of the detected target shapes for convenience of explanation (for example, a square surrounding each numeral portion) The minimum bounding box may be easily inferred that it is not the edge detected.

In the case of FIG. 5, no target shape is detected in the first edge image 50-1 and nine target shapes are detected in the second edge image 51-1. Therefore, since the number of target shapes detected in the second edge image 51-1 is greater than the number of target shapes detected in the first edge image 50-1, the determination module 112 determines that the digital images , 50, 51) can be determined as images taken of a physical object.

6 is a diagram for explaining an example of detecting a target object according to a digital image determination method according to an embodiment of the present invention.

5A and 6A, FIG. 6A is a diagram showing the contour (for example, 50-4 and 50-5) of the edge corresponding to the card number 8 in the first edge image 50-1 shown in FIG. 5 FIG. 6B conceptually shows a drawing in which the contour 51-4 of the edge corresponding to the same card number 8 is extracted in the second edge image 51-1 shown in FIG.

6A, the detection module 113 generates a minimum bounding box (e.g., 50-6, 50-7) of each of the detected contours (e.g., 50-4, 50-5) It can be like a bar. In the case of FIG. 6B, the detection module 113 may be as shown in FIG. 6B by generating a minimum bounding box (e.g., 51-5) of the detected contour (e.g., 51-4). Therefore, when all the edges representing the outline of the target shape (e.g., a number) are detected, the size of the minimum bounding box 51-5 corresponding to the contour 51-4 of the edge as shown in Fig. (E.g., shown in FIG. 5B) corresponding to the original target shape (card number displayed on the actual card), or may only have an error within a certain range. In such a case, the detection module 113 may determine that the target shape has been detected.

However, if all of the edges representing the outline of the target shape are not detected but only partially detected, the minimum bounding box corresponding to each of the contours 50-4 and 50-5, as shown in Fig. 6A, (50-6, 50-7) is smaller than the size of the reference bounding box. In this case, it can be determined that the target shape is not detected.

The detection module 113 may calculate the number of detected target shapes from each of the edge images (or the analysis images that have undergone at least one edge processing of edge processing of the edge image) in this manner, The module 112 can perform the object object photographing authentication based on the calculated number.

On the other hand, Figs. 7 to 12 show the results of simulating the technical idea of the present invention by setting different types of cards and different external illumination conditions from Fig.

FIGS. 7 to 12 are views for explaining an example of determining whether a plurality of images are images taken of a physical object according to a digital image determination method according to another embodiment of the present invention.

FIGS. 7 and 8 show simulation results when an actual card is photographed in a relatively dark lighting environment, and FIG. 9 shows simulation results when an actual card is photographed in a relatively bright lighting environment. FIGS. 10 to 12 show simulation results obtained by photographing images of two different cards, that is, two-dimensional images. FIG. 7 to 12 show an example of performing the object object photographing authentication using the number of detected target shapes.

7, the number of target shapes detected from the first edge image 52-1 and the second edge image 53-1 corresponding to the first digital image 52 and the second digital image 53 are respectively 0 and 2, respectively. That is, it can be seen that more target features are detected from the second edge image 53-1, so that the determination system 100, 100-1 can determine that the first digital image 52 and the second digital image 53) can be determined as the images of the real objects.

8, the number of target shapes detected from the first edge image 54-1 and the second edge image 55-1 corresponding to the first digital image 54 and the second digital image 55 is 0 and 6, respectively. It can be seen that more target features are detected from the second edge image 55-1 so that the determination system 100,100-1 can detect the first digital image 54 and the second digital image 55, Can be determined as images taken of a real object.

9, the number of target shapes detected from the first edge image 56-1 and the second edge image 57-1 corresponding to the first digital image 56 and the second digital image 57, respectively, 0 and 8, respectively. Thus, it can be seen that more target shapes are detected from the second edge image 57-1 so that the determination system 100, 100-1 can determine that the first digital image 56 and the second digital image 57 ) Can be determined as images taken of a real object.

10, the number of target shapes detected from the first edge image 58-1 and the second edge image 59-1 corresponding to the first digital image 58 and the second digital image 59, respectively, 0, and 0, respectively. That is, if neither the target shape is detected from the second edge image 59-1 and the first edge image 58-1, or more target shapes are detected from the first edge image 58-1, The judgment system 100, 100-1 may judge the first digital image 58 and the second digital image 59 as image picked-up images.

11, the number of target shapes detected from the first edge image 60-1 and the second edge image 61-1 corresponding to each of the first digital image 60 and the second digital image 61 is 0, and 0, respectively. That is, since the target shape is not detected from both the second edge image 61-1 and the first edge image 58-1, the determination system 100, 100-1 determines that the first digital image 58 ) And the second digital image 59 as image picked-up images.

12, the number of target shapes detected from the first edge image 62-1 and the second edge image 63-1 corresponding to the first digital image 62 and the second digital image 63, respectively, 12 and 8, respectively. That is, since more target shapes are detected from the first edge image 58-1, the determination system 100, 100-1 determines the first digital image 58 and the second digital image 59 as It is possible to judge them as image-captured images.

The digital image judgment system and method according to the technical idea of the present invention can be variously adopted for a photo counterfeiting and anti-theft service besides non-face person authentication, card occupancy authentication and settlement. For example, it can be applied to a system of an insurance company that requires confirmation of whether or not a mileage or a black box is installed, a service that requires judgment of whether or not an article photograph is online, and the like. In addition, it can be applied to various services for confirming online photos.

On the other hand, according to an embodiment, the digital image determination system 100, 100-1, the data processing system 30, and / or the application system 40 may comprise a processor and a memory for storing programs executed by the processor . The processor may include a single-core CPU or a multi-core CPU. The memory may include high speed random access memory and may include non-volatile memory such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state memory devices. Access to the memory by the processor and other components can be controlled by the memory controller. Here, the program may be executed by a processor by causing the digital image determination system (e.g., 100), the data processing system 30, and / or the application system 40 according to the present embodiment to perform the above- .

Meanwhile, the digital image determination method according to an exemplary embodiment of the present invention may be implemented in the form of a computer-readable program command and stored in a computer-readable recording medium. The control program and the target program May also be stored in a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of software.

Examples of the computer-readable recording medium include magnetic media such as a hard disk, a floppy disk and a magnetic tape, optical media such as CD-ROM and DVD, a floptical disk, And hardware devices that are specially configured to store and execute program instructions such as magneto-optical media and ROM, RAM, flash memory, and the like. The above-mentioned medium may also be a transmission medium such as a light or metal wire, wave guide, etc., including a carrier wave for transmitting a signal designating a program command, a data structure and the like. The computer readable recording medium may also be distributed over a networked computer system so that computer readable code can be stored and executed in a distributed manner.

Examples of program instructions include machine language code such as those produced by a compiler, as well as devices for processing information electronically using an interpreter or the like, for example, a high-level language code that can be executed by a computer.

The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

It is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. .

Claims (19)

An acquiring module for acquiring a plurality of digital images including a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state on the same object; And
And a control module for determining whether the plurality of digital images are images of a three-dimensional real object or a two-dimensional image based on the plurality of digital images acquired by the acquisition module,
The control module includes:
Analyzing the first digital image and the second digital image, and determining whether the digital images are three-dimensional real objects or two-dimensional images based on the analysis results.
2. The method of claim 1, wherein the first digital image and the second digital image are each a digital image,
Wherein the digital image judging system is installed or the illuminating device of the image photographing device performing communication with the digital image judging system is an image photographed in an inactivated state and in an activated state.
The apparatus of claim 1,
A first edge image that detects an edge in all or a predetermined predetermined area of the first digital image from the first digital image and a second edge image that detects an edge in the entirety of the second digital image or the specific An edge detection module for generating a second edge image that detects an edge in the region; And
Wherein the edge detection module analyzes edges of the first edge image and the second edge image generated by the edge detection module to determine whether the digital images are three-dimensional object images or two-dimensional image images The digital image determination system comprising:
The apparatus of claim 3,
Comparing the at least one of the first edge image and the intensity of the edge or the edge included in the second edge image and determining whether the digital images have photographed the physical object based on the comparison result, system.
The apparatus of claim 3,
The number of the first target shape and the number of the second target shape, which means the number of the predetermined target shape detected from each of the first analysis image and the second analysis image corresponding to each of the first edge image and the second edge image, To determine whether the digital images have been photographed by a real object.
6. The apparatus of claim 5,
Extracting contours of respective edges included in each of the first analysis image and the second analysis image, and calculating the first target shape number and the second target shape number based on the extracted contours Further comprising a detection module.
6. The image processing apparatus according to claim 5, wherein the first analysis image and the second analysis image include:
The first edge image and the second edge image are blurred images at a predetermined level at least once,
Wherein the size of the first edge image and the size of the second edge image is at least once reduced to a predetermined level.
3. The image capturing apparatus according to claim 2,
The first digital image in a state in which the illumination device is inactivated and the second digital image in a state in which the illumination device is activated are continuously The digital image determination system comprising:
A storage medium in which a program is stored; And
And a processor for executing the program,
The processor executes the program,
Analyzing a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state on the same object and determining whether the digital images have photographed a three- A data processing system for determining whether a two-dimensional image has been taken.
An application system installed in an image photographing apparatus,
An interface module for receiving a photographing request signal from a user; And
A control module for controlling an illumination device provided in the image photographing apparatus and an image photographing sensor for photographing an image,
The control module includes:
And controls to shoot a first digital image in a first illumination state and a second digital image in a second illumination state continuously on a predetermined object in response to the shooting request signal.
11. The method of claim 10, wherein the first digital image and the second digital image comprise:
Wherein the first digital image and the second digital image are analyzed by a predetermined digital image determination system to determine whether a three-dimensional real object has been photographed or a two-dimensional image has been photographed.
Obtaining a plurality of digital images including a first digital image photographed in a first illumination state and a second digital image photographed in a second illumination state on the same object; And
Analyzing the acquired first digital image and the second digital image, and determining whether the plurality of digital images have photographed the three-dimensional object or the two-dimensional image based on the analysis result Wherein the digital image determination method comprises:
13. The image processing method according to claim 12, further comprising the steps of: analyzing the obtained first digital image and the second digital image; determining whether the plurality of digital images have photographed the three- Wherein the step of determining whether the one-
A first edge image from which an edge has been detected from all of the first digital image or from a predetermined specific area from the first digital image and an edge from all or a predetermined specific area of the second digital image from the second digital image Generating a second edge image;
And analyzing an edge of each of the generated first edge image and the generated second edge image to determine whether the digital images have taken a three-dimensional real object or a two-dimensional image, How to judge.
14. The method of claim 13, further comprising analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images are three-dimensional object images or two-dimensional image images Lt; / RTI >
Comparing at least one of the first edge image and the intensity of the edge or the edge included in the second edge image and determining whether the digital images have photographed the physical object based on the comparison result A digital image judging method.
14. The method of claim 13, further comprising analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images are three-dimensional object images or two-dimensional image images Lt; / RTI >
The number of the first target shape and the number of the second target shape, which means the number of the predetermined target shape detected from each of the first analysis image and the second analysis image corresponding to each of the first edge image and the second edge image, And determining whether the digital images are photographed on a physical object.
15. The method of claim 14, further comprising analyzing edges of each of the generated first edge image and second edge image to determine whether the digital images are taken of a three-dimensional object or a two-dimensional image Lt; / RTI >
Extracting contours of respective edges included in each of the first analysis image and the second analysis image, and calculating the first target shape number and the second target shape number based on the extracted contours Further comprising the steps of:
16. The image processing system according to claim 15, wherein the first analysis image and the second analysis image include:
The first edge image and the second edge image are blurred at least once to a predetermined level, or the size of the first edge image and the second edge image is at least once set to a predetermined schedule And the size of the image is reduced to a level that is smaller than the predetermined size.
A method performed by an application installed in an image photographing apparatus,
Receiving a photographing request signal from a user;
And continuously photographing a first digital image in a first illumination state and a second digital image in a second illumination state on a predetermined object in response to the photographing request signal.
19. The method of claim 18,
Wherein the first digital image and the second digital image are transmitted to a predetermined digital image determination system,
Wherein the first digital image and the second digital image are analyzed by the digital image determination system to determine whether a three-dimensional real object has been photographed or a two-dimensional image has been photographed.

Images