CN117292465B - Intelligent access control anti-theft system based on wireless network - Google Patents
Intelligent access control anti-theft system based on wireless network Download PDFInfo
- Publication number
- CN117292465B CN117292465B CN202311164797.4A CN202311164797A CN117292465B CN 117292465 B CN117292465 B CN 117292465B CN 202311164797 A CN202311164797 A CN 202311164797A CN 117292465 B CN117292465 B CN 117292465B
- Authority
- CN
- China
- Prior art keywords
- module
- determining
- preset
- voice signal
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 238000012795 verification Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 5
- 230000001815 facial effect Effects 0.000 claims description 46
- 230000002159 abnormal effect Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 28
- 238000005070 sampling Methods 0.000 claims description 21
- 230000009467 reduction Effects 0.000 claims description 19
- 238000001228 spectrum Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 10
- 210000000056 organ Anatomy 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 4
- 210000003128 head Anatomy 0.000 claims description 4
- 238000010183 spectrum analysis Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000007261 regionalization Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00309—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated with bidirectional data transmission between data carrier and locks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00571—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys operated by interacting with a central unit
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an intelligent access control anti-theft system based on a wireless network, which comprises: an access control body; the first acquisition module is used for acquiring a monitoring image comprising a user in a preset area of the access control body; the first identification module is used for identifying the monitoring image and determining a first identification result; the second acquisition module is used for randomly generating verification information and prompting a user to read when the first recognition result is determined to be the recognition result to be verified, and acquiring a voice signal of the user in the reading process; the second recognition module is used for recognizing the voice signal and determining a second recognition result; the first determining module is used for sending an opening instruction to the door lock control module when the identity verification of the user is determined to pass according to the second identification result; and the door lock control module is used for receiving the opening instruction and executing the opening instruction. The method and the device realize accurate identification of the user identity, provide convenience for the user and improve the user experience.
Description
Technical Field
The invention relates to the technical field of burglary prevention, in particular to an intelligent access control burglary-resisting system based on a wireless network.
Background
At present, various intelligent access control devices are arranged in various places and used for intelligently managing whether a user can enter. In the prior art, the identity of a user is usually identified by an image, but the user cannot accurately identify the identity because the user wears a cap, a mask and the like, and the user needs to remove the cap, the mask and the like, so that the intelligent access control is inconvenient; because users have various makeup, make-up and other reasons, the users cannot accurately identify the makeup, the users need to remove the makeup, and the user experience is poor.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, the invention aims to provide an intelligent access control anti-theft system based on a wireless network, which solves the technical problems of inaccuracy and inconvenience in image recognition of the identity of a user.
In order to achieve the above object, an embodiment of the present invention provides an intelligent access control anti-theft system based on a wireless network, including:
An access control body;
the first acquisition module is used for acquiring a monitoring image comprising a user in a preset area of the access control body;
The first identification module is used for identifying the monitoring image and determining a first identification result;
the second acquisition module is used for randomly generating verification information and prompting a user to read when the first recognition result is determined to be the recognition result to be verified, and acquiring a voice signal of the user in the reading process;
the second recognition module is used for recognizing the voice signal and determining a second recognition result;
The first determining module is used for sending an opening instruction to the door lock control module when the identity verification of the user is determined to pass according to the second identification result;
and the door lock control module is used for receiving the opening instruction and executing the opening instruction.
According to some embodiments of the invention, the first acquisition module includes:
The human body sensing module is used for sensing whether a user is included in a preset area of the access control body, and sending a shooting instruction to the shooting module when the user is determined to be included;
And the shooting module is used for receiving and executing shooting instructions and generating monitoring images.
According to some embodiments of the invention, the first identification module comprises:
The segmentation module is used for carrying out preliminary recognition on the monitoring image, and segmenting the monitoring image based on a preliminary recognition result to obtain a face image and a body image;
The first matching module is used for analyzing the facial image and determining facial features; matching the facial features with preset facial features in a preset user database, determining a preset facial image corresponding to the preset facial feature with the highest first matching degree as a target preset facial image, and determining a preset body image corresponding to the target preset facial image;
the second matching module is used for analyzing the body image and determining the body characteristics; matching the body characteristics with preset body characteristics included in a preset body image, and determining a second matching degree;
the second determining module is used for carrying out weighted calculation according to the first matching degree and the second matching degree of the facial features and the preset facial features of the target preset facial image, and determining a third matching degree;
the judging module is used for judging whether the third matching degree is in a preset range or not, and determining a first identification result according to the judging result.
According to some embodiments of the invention, the first matching module includes:
the denoising module is used for carrying out binarization processing on the face image, dividing the background pixel point from the target pixel point, removing the background pixel point and reserving the target pixel point; the target pixel points comprise pixel points of the outer outline of the head, eyes, nose and mouth;
And a third determining module for determining attribute information of each organ and distance information between each organ as facial features according to the target pixel points.
According to some embodiments of the invention, the second matching module includes:
the fourth determining module is used for carrying out edge detection on the body image and determining contour information of each limb;
A fifth determining module, configured to determine limb proportion information according to contour information of each limb; contour information and proportion information of each limb are taken as body characteristics.
According to some embodiments of the invention, the second identification module comprises:
the enhancement module is used for enhancing the voice signal to obtain a target voice signal;
A filtering module for:
Performing voice segmentation processing on the target voice signals to obtain a plurality of sub-target voice signals, and determining a first short-time energy parameter of each sub-target voice signal;
performing discretization processing on the target voice signal, and performing sampling, quantization and coding processing on the discretized target voice signal to obtain a digital voice signal;
Performing voice segmentation processing on the digital voice signals to obtain a plurality of sub-digital voice signals, and determining a second short-time energy parameter of each sub-digital voice signal;
Calculating the difference value between the first short-time energy parameter of the sub-target voice signal and the second short-time energy parameter of the corresponding sub-digital voice signal, and carrying out summation processing to obtain a difference total value;
Inquiring a preset data table according to the total difference value, determining a filtering coefficient, and performing filtering processing on the target voice signal according to the filtering coefficient to obtain a filtered voice signal;
A sixth determining module, configured to:
Extracting the characteristics of the filtered voice signals, and determining the voice characteristics of a user;
And matching the sound characteristics with preset sound characteristics of a user corresponding to the target preset facial image, calculating to obtain a second matching degree, and taking a comparison result of the second matching degree and a preset threshold value as a second recognition result.
According to some embodiments of the invention, the enhancement module comprises:
The analysis module is used for carrying out spectrum analysis processing on the voice signal and determining a spectrogram corresponding to the voice signal;
The comparison module is used for comparing the amplitude value of each frequency spectrum component in the frequency spectrum chart with a preset amplitude value respectively, and determining a voice signal to be processed and a reserved voice signal according to the comparison result; the semantic signal to be processed is a signal corresponding to a frequency spectrum component with an amplitude value smaller than a preset amplitude value; the reserved voice signal is a signal corresponding to a frequency spectrum component with an amplitude value larger than or equal to a preset amplitude value;
The adjusting module is used for adjusting the amplitude value of the voice signal to be processed to obtain an adjusting voice signal, and determining a target voice signal according to the adjusting voice signal and the reserved voice signal.
According to some embodiments of the invention, the noise reduction module is further configured to:
before a first identification module identifies a monitoring image, acquiring gray values of all pixel points in the monitoring image, and calculating an average gray value;
Calculating the difference value between the gray value and the average gray value of each pixel point, and taking the pixel point with the difference value larger than the preset gray threshold value as an abnormal pixel point;
determining a region to be processed by taking the abnormal pixel point as a circle center and a preset distance as a radius; determining a first pixel point and a second pixel point in a region to be processed; the first pixel point is the pixel point with the largest difference value between the gray value in the area to be processed and the gray value of the abnormal pixel point; the first pixel point is a pixel point with the minimum difference value between the gray value in the region to be processed and the gray value of the abnormal pixel point;
determining a first distance value between the abnormal pixel point and the first pixel point and a second distance value between the abnormal pixel point and the second pixel point;
inquiring a preset first distance value-second distance value-noise reduction parameter data table according to the first distance value and the second distance value, determining a target noise reduction parameter, and performing noise reduction treatment on the region to be treated based on the target noise reduction parameter to obtain a noise-reduced monitoring image.
According to some embodiments of the invention, further comprising: the vibration sensing module is used for detecting a vibration signal of the access control body and converting the vibration signal into a vibration value; and when the vibration value is determined to be larger than the preset vibration value, sending out an alarm prompt.
According to some embodiments of the invention, further comprising: the detection module is used for detecting the current signal on the door lock control module and collecting signal waves of the current signal based on a preset sampling rate in a preset time period;
Dividing the signal wave into M sections of sub-signal waves, wherein the time length of each section of sub-signal wave is N milliseconds;
Acquiring sampling values of all sampling points of the sub-signal wave before N/2 milliseconds, and determining a maximum sampling value; taking the sub-signal wave with the maximum sampling value smaller than the preset threshold value as an abnormal sub-signal wave, and removing the abnormal sub-signal wave; obtaining a target current signal according to the sub-signal wave with the maximum sampling value being greater than or equal to a preset threshold value;
And extracting the characteristics of the target current signal, determining the current characteristics, comparing the current characteristics with preset current characteristics, and sending out an alarm prompt when the current characteristics are inconsistent with the preset current characteristics.
The invention provides an intelligent access control anti-theft system based on a wireless network, which is characterized in that firstly, preliminary identification is carried out based on image identification, whether a first identification result needs to be verified again is determined, when the first identification result needs to be verified again is determined, the identity of a user is verified again based on voice identification, the accuracy of the user identity verification is improved, meanwhile, inaccuracy of the user identity verification caused by external changes of the user, such as makeup, mask and the like, is avoided, the convenience is improved, and the user experience is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of a wireless network-based intelligent access control anti-theft system in accordance with one embodiment of the present invention;
FIG. 2 is a block diagram of a first identification module according to one embodiment of the invention;
Fig. 3 is a block diagram of a first matching module according to one embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
As shown in fig. 1, an embodiment of the present invention provides an intelligent access control anti-theft system based on a wireless network, including:
An access control body;
the first acquisition module is used for acquiring a monitoring image comprising a user in a preset area of the access control body;
The first identification module is used for identifying the monitoring image and determining a first identification result;
the second acquisition module is used for randomly generating verification information and prompting a user to read when the first recognition result is determined to be the recognition result to be verified, and acquiring a voice signal of the user in the reading process;
the second recognition module is used for recognizing the voice signal and determining a second recognition result;
The first determining module is used for sending an opening instruction to the door lock control module when the identity verification of the user is determined to pass according to the second identification result;
and the door lock control module is used for receiving the opening instruction and executing the opening instruction.
The working principle of the technical scheme is as follows: in this embodiment, the preset area is an area for performing authentication corresponding to the entrance guard body.
In this embodiment, the first recognition result includes a recognition result to be verified and a determination recognition result. The identification result to be verified is based on matching of the image of the user with a preset stored image, and the determined matching degree is within a preset range. The preset range is 70-90. And when the determined matching degree is smaller than 70, the verification is failed, and the door lock control module cannot be opened. When it is determined that the verification is greater than 90, the door lock control module opens.
In this embodiment, the authentication information may be random literal characters.
In this embodiment, the second recognition result is a comparison result of a second matching degree of the sound feature and the preset sound feature of the user corresponding to the target preset face image determined in the first recognition result, and the second matching degree is determined to be greater than or equal to the preset threshold value, and indicates that the authentication of the user passes, and the second matching degree is determined to be less than the preset threshold value, and indicates that the authentication of the user does not pass.
The beneficial effects of the technical scheme are that: firstly, based on image recognition, preliminary recognition is carried out, whether a first recognition result needs to be verified again is determined, when the first recognition result needs to be verified again is determined, based on voice recognition, the identity of a user is verified again, the accuracy of user identity verification is improved, meanwhile, inaccuracy of the user identity verification caused by external changes of the user, such as makeup, mask carrying and the like, is avoided, convenience is brought to the user, and user experience is improved.
According to some embodiments of the invention, the first acquisition module includes:
The human body sensing module is used for sensing whether a user is included in a preset area of the access control body, and sending a shooting instruction to the shooting module when the user is determined to be included;
And the shooting module is used for receiving and executing shooting instructions and generating monitoring images.
The working principle of the technical scheme is as follows: in this embodiment, the human body sensing module is an infrared sensing module.
The beneficial effects of the technical scheme are that: when the preset area of the access control body is determined to comprise a user, the shooting module is controlled to shoot, and waste of resources is avoided.
As shown in fig. 2, according to some embodiments of the invention, the first identification module includes:
The segmentation module is used for carrying out preliminary recognition on the monitoring image, and segmenting the monitoring image based on a preliminary recognition result to obtain a face image and a body image;
The first matching module is used for analyzing the facial image and determining facial features; matching the facial features with preset facial features in a preset user database, determining a preset facial image corresponding to the preset facial feature with the highest first matching degree as a target preset facial image, and determining a preset body image corresponding to the target preset facial image;
the second matching module is used for analyzing the body image and determining the body characteristics; matching the body characteristics with preset body characteristics included in a preset body image, and determining a second matching degree;
the second determining module is used for carrying out weighted calculation according to the first matching degree and the second matching degree of the facial features and the preset facial features of the target preset facial image, and determining a third matching degree;
the judging module is used for judging whether the third matching degree is in a preset range or not, and determining a first identification result according to the judging result.
The technical scheme has the working principle and beneficial effects that: the face image is a face image of the user; the body image is an image below the head of the user and is mainly used for displaying the body characteristics and the body posture of the user. Dividing a user in the monitoring image to obtain a face image and a body image; the facial image and the body image are respectively analyzed and matched, so that inaccuracy of user identity recognition caused by the fact that only the facial image is analyzed and the body image is ignored in the prior art is avoided. The second determining module is used for carrying out weighted calculation according to the first matching degree and the second matching degree of the facial features and the preset facial features of the target preset facial image, and determining a third matching degree; the judging module is used for judging whether the third matching degree is in a preset range or not, and determining a first identification result according to the judging result. The method is convenient for accurately determining the first recognition result, realizes comprehensive recognition of the face and the body of the user based on image recognition, is convenient for improving the accuracy of recognizing the identity of the user based on the image, and also avoids false identity recognition caused by fake user face so as to realize the anti-theft function.
As shown in fig. 3, according to some embodiments of the present invention, the first matching module includes:
the denoising module is used for carrying out binarization processing on the face image, dividing the background pixel point from the target pixel point, removing the background pixel point and reserving the target pixel point; the target pixel points comprise pixel points of the outer outline of the head, eyes, nose and mouth;
And a third determining module for determining attribute information of each organ and distance information between each organ as facial features according to the target pixel points.
The working principle of the technical scheme is as follows: in this embodiment, the attribute information is the size, shape of the organ.
The beneficial effects of the technical scheme are that: the denoising module is used for carrying out binarization processing on the face image, dividing the background pixel point from the target pixel point, removing the background pixel point and reserving the target pixel point; and a third determining module for determining attribute information of each organ and distance information between each organ as facial features according to the target pixel points. Facilitating the determination of accurate facial features.
According to some embodiments of the invention, the second matching module includes:
the fourth determining module is used for carrying out edge detection on the body image and determining contour information of each limb;
A fifth determining module, configured to determine limb proportion information according to contour information of each limb; contour information and proportion information of each limb are taken as body characteristics.
The technical scheme has the working principle and beneficial effects that: the fourth determining module is used for carrying out edge detection on the body image and determining contour information of each limb; a fifth determining module, configured to determine limb proportion information according to contour information of each limb; contour information and proportion information of each limb are taken as body characteristics. Accurate determination of body features, i.e., body gestures, characterizing a user is facilitated.
According to some embodiments of the invention, the second identification module comprises:
the enhancement module is used for enhancing the voice signal to obtain a target voice signal;
A filtering module for:
Performing voice segmentation processing on the target voice signals to obtain a plurality of sub-target voice signals, and determining a first short-time energy parameter of each sub-target voice signal;
performing discretization processing on the target voice signal, and performing sampling, quantization and coding processing on the discretized target voice signal to obtain a digital voice signal;
Performing voice segmentation processing on the digital voice signals to obtain a plurality of sub-digital voice signals, and determining a second short-time energy parameter of each sub-digital voice signal;
Calculating the difference value between the first short-time energy parameter of the sub-target voice signal and the second short-time energy parameter of the corresponding sub-digital voice signal, and carrying out summation processing to obtain a difference total value;
Inquiring a preset data table according to the total difference value, determining a filtering coefficient, and performing filtering processing on the target voice signal according to the filtering coefficient to obtain a filtered voice signal;
A sixth determining module, configured to:
Extracting the characteristics of the filtered voice signals, and determining the voice characteristics of a user;
And matching the sound characteristics with preset sound characteristics of a user corresponding to the target preset facial image, calculating to obtain a second matching degree, and taking a comparison result of the second matching degree and a preset threshold value as a second recognition result.
The working principle of the technical scheme is as follows: the enhancement module carries out enhancement processing on the voice signal to obtain a target voice signal, so that the identifiability of the target voice signal is improved, the influence of noise on recognition is inhibited, and the voice recognition is more accurate.
In this embodiment, the manner in which the target speech signal and the digital speech signal are subjected to the speech division processing is the same as the number of divisions and the node position.
In this embodiment, the sub-target speech signal and the corresponding sub-digital speech signal are compared as a group based on the consistency of the two speech segmentation processes.
In this embodiment, the preset data table is a difference total value-filter coefficient data table.
The beneficial effects of the technical scheme are that: firstly, carrying out signal enhancement on a voice signal to obtain a target voice signal; and filtering the target voice signal to obtain a filtered voice signal, and eliminating the influence of noise. The accuracy of determining the sound characteristics of the user is improved, and the accuracy of determining the second recognition result is further improved.
According to some embodiments of the invention, the enhancement module comprises:
The analysis module is used for carrying out spectrum analysis processing on the voice signal and determining a spectrogram corresponding to the voice signal;
The comparison module is used for comparing the amplitude value of each frequency spectrum component in the frequency spectrum chart with a preset amplitude value respectively, and determining a voice signal to be processed and a reserved voice signal according to the comparison result; the semantic signal to be processed is a signal corresponding to a frequency spectrum component with an amplitude value smaller than a preset amplitude value; the reserved voice signal is a signal corresponding to a frequency spectrum component with an amplitude value larger than or equal to a preset amplitude value;
The adjusting module is used for adjusting the amplitude value of the voice signal to be processed to obtain an adjusting voice signal, and determining a target voice signal according to the adjusting voice signal and the reserved voice signal.
The technical scheme has the working principle and beneficial effects that: the analysis module is used for carrying out spectrum analysis processing on the voice signal and determining a spectrogram corresponding to the voice signal; the comparison module is used for comparing the amplitude value of each frequency spectrum component in the frequency spectrum chart with a preset amplitude value respectively, and determining a voice signal to be processed and a reserved voice signal according to the comparison result; the semantic signal to be processed is a signal corresponding to a frequency spectrum component with an amplitude value smaller than a preset amplitude value; the reserved voice signal is a signal corresponding to a frequency spectrum component with an amplitude value larger than or equal to a preset amplitude value; the adjusting module is used for adjusting the amplitude value of the voice signal to be processed, so that the amplitude value of the voice signal to be processed is equal to a preset amplitude value, effective recognition is convenient to conduct, detail characteristics are reserved, and the loss of the detail characteristics caused by the fact that the amplitude value is smaller and cannot be recognized is avoided. And obtaining an adjusting voice signal, and determining a target voice signal according to the adjusting voice signal and the reserved voice signal. The accuracy of the target voice signal is improved.
According to some embodiments of the invention, the noise reduction module is further configured to:
before a first identification module identifies a monitoring image, acquiring gray values of all pixel points in the monitoring image, and calculating an average gray value;
Calculating the difference value between the gray value and the average gray value of each pixel point, and taking the pixel point with the difference value larger than the preset gray threshold value as an abnormal pixel point;
determining a region to be processed by taking the abnormal pixel point as a circle center and a preset distance as a radius; determining a first pixel point and a second pixel point in a region to be processed; the first pixel point is the pixel point with the largest difference value between the gray value in the area to be processed and the gray value of the abnormal pixel point; the first pixel point is a pixel point with the minimum difference value between the gray value in the region to be processed and the gray value of the abnormal pixel point;
determining a first distance value between the abnormal pixel point and the first pixel point and a second distance value between the abnormal pixel point and the second pixel point;
inquiring a preset first distance value-second distance value-noise reduction parameter data table according to the first distance value and the second distance value, determining a target noise reduction parameter, and performing noise reduction treatment on the region to be treated based on the target noise reduction parameter to obtain a noise-reduced monitoring image.
The technical scheme has the working principle and beneficial effects that: determining an abnormal pixel point based on the noise reduction module, and determining a region to be processed by taking the abnormal pixel point as a circle center and a preset distance as a radius; the method comprises the steps of determining characteristic points in a region to be processed, namely a first pixel point and a second pixel point, determining characteristic parameters, namely a first distance value between an abnormal pixel point and the first pixel point and a second distance value between the abnormal pixel point and the second pixel point, further accurately determining noise reduction parameters of the region to be processed, and carrying out noise reduction based on regionalization, so that the noise reduction accuracy is improved, and further a more accurate monitoring image is obtained.
According to some embodiments of the invention, further comprising: the vibration sensing module is used for detecting a vibration signal of the access control body and converting the vibration signal into a vibration value; and when the vibration value is determined to be larger than the preset vibration value, sending out an alarm prompt.
The beneficial effects of the technical scheme are that: timely finding out whether a user runs the entrance guard and timely taking corresponding measures.
According to some embodiments of the invention, further comprising: the detection module is used for detecting the current signal on the door lock control module and collecting signal waves of the current signal based on a preset sampling rate in a preset time period;
Dividing the signal wave into M sections of sub-signal waves, wherein the time length of each section of sub-signal wave is N milliseconds;
Acquiring sampling values of all sampling points of the sub-signal wave before N/2 milliseconds, and determining a maximum sampling value; taking the sub-signal wave with the maximum sampling value smaller than the preset threshold value as an abnormal sub-signal wave, and removing the abnormal sub-signal wave; obtaining a target current signal according to the sub-signal wave with the maximum sampling value being greater than or equal to a preset threshold value;
And extracting the characteristics of the target current signal, determining the current characteristics, comparing the current characteristics with preset current characteristics, and sending out an alarm prompt when the current characteristics are inconsistent with the preset current characteristics.
The working principle of the technical scheme is as follows: in this embodiment, the target current signal is an effective current signal.
The beneficial effects of the technical scheme are that: the method is convenient for accurately eliminating abnormal sub-signal waves, determining effective target current signals, further improving accuracy of determining current characteristics, comparing the current characteristics with preset current characteristics, sending out alarm prompt when the current characteristics are determined to be inconsistent with the preset current characteristics, and conveniently and timely finding out whether a door lock control module fails or not, thereby improving safety and reliability of the door lock anti-theft system.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. An intelligent access control anti-theft system based on wireless network, which is characterized by comprising:
An access control body;
the first acquisition module is used for acquiring a monitoring image comprising a user in a preset area of the access control body;
The first identification module is used for identifying the monitoring image and determining a first identification result;
the second acquisition module is used for randomly generating verification information and prompting a user to read when the first recognition result is determined to be the recognition result to be verified, and acquiring a voice signal of the user in the reading process;
the second recognition module is used for recognizing the voice signal and determining a second recognition result;
The first determining module is used for sending an opening instruction to the door lock control module when the identity verification of the user is determined to pass according to the second identification result;
The door lock control module is used for receiving the opening instruction and executing the opening instruction;
The first identification module includes:
The segmentation module is used for carrying out preliminary recognition on the monitoring image, and segmenting the monitoring image based on a preliminary recognition result to obtain a face image and a body image;
The first matching module is used for analyzing the facial image and determining facial features; matching the facial features with preset facial features in a preset user database, determining a preset facial image corresponding to the preset facial feature with the highest first matching degree as a target preset facial image, and determining a preset body image corresponding to the target preset facial image;
the second matching module is used for analyzing the body image and determining the body characteristics; matching the body characteristics with preset body characteristics included in a preset body image, and determining a second matching degree;
the second determining module is used for carrying out weighted calculation according to the first matching degree and the second matching degree of the facial features and the preset facial features of the target preset facial image, and determining a third matching degree;
The judging module is used for judging whether the third matching degree is in a preset range or not, and determining a first identification result according to the judging result;
the second identification module includes:
the enhancement module is used for enhancing the voice signal to obtain a target voice signal;
A filtering module for:
Performing voice segmentation processing on the target voice signals to obtain a plurality of sub-target voice signals, and determining a first short-time energy parameter of each sub-target voice signal;
performing discretization processing on the target voice signal, and performing sampling, quantization and coding processing on the discretized target voice signal to obtain a digital voice signal;
Performing voice segmentation processing on the digital voice signals to obtain a plurality of sub-digital voice signals, and determining a second short-time energy parameter of each sub-digital voice signal;
Calculating the difference value between the first short-time energy parameter of the sub-target voice signal and the second short-time energy parameter of the corresponding sub-digital voice signal, and carrying out summation processing to obtain a difference total value;
Inquiring a preset data table according to the total difference value, determining a filtering coefficient, and performing filtering processing on the target voice signal according to the filtering coefficient to obtain a filtered voice signal;
A sixth determining module, configured to:
Extracting the characteristics of the filtered voice signals, and determining the voice characteristics of a user;
matching the sound features with preset sound features of a user corresponding to the target preset facial image, calculating to obtain a second matching degree, and taking a comparison result of the second matching degree and a preset threshold value as a second recognition result;
the enhancement module comprises:
The analysis module is used for carrying out spectrum analysis processing on the voice signal and determining a spectrogram corresponding to the voice signal;
The comparison module is used for comparing the amplitude value of each frequency spectrum component in the frequency spectrum chart with a preset amplitude value respectively, and determining a voice signal to be processed and a reserved voice signal according to the comparison result; the semantic signal to be processed is a signal corresponding to a frequency spectrum component with an amplitude value smaller than a preset amplitude value; the reserved voice signal is a signal corresponding to a frequency spectrum component with an amplitude value larger than or equal to a preset amplitude value;
The adjusting module is used for adjusting the amplitude value of the voice signal to be processed to obtain an adjusting voice signal, and determining a target voice signal according to the adjusting voice signal and the reserved voice signal.
2. The wireless network-based intelligent access control anti-theft system of claim 1, wherein the first acquisition module comprises:
The human body sensing module is used for sensing whether a user is included in a preset area of the access control body, and sending a shooting instruction to the shooting module when the user is determined to be included;
And the shooting module is used for receiving and executing shooting instructions and generating monitoring images.
3. The wireless network-based intelligent access control anti-theft system of claim 1, wherein the first matching module comprises:
the denoising module is used for carrying out binarization processing on the face image, dividing the background pixel point from the target pixel point, removing the background pixel point and reserving the target pixel point; the target pixel points comprise pixel points of the outer outline of the head, eyes, nose and mouth;
And a third determining module for determining attribute information of each organ and distance information between each organ as facial features according to the target pixel points.
4. The wireless network-based intelligent access control anti-theft system of claim 1, wherein the second matching module comprises:
the fourth determining module is used for carrying out edge detection on the body image and determining contour information of each limb;
A fifth determining module, configured to determine limb proportion information according to contour information of each limb; contour information and proportion information of each limb are taken as body characteristics.
5. The intelligent access control anti-theft system based on a wireless network of claim 1, further comprising a noise reduction module for:
before a first identification module identifies a monitoring image, acquiring gray values of all pixel points in the monitoring image, and calculating an average gray value;
Calculating the difference value between the gray value and the average gray value of each pixel point, and taking the pixel point with the difference value larger than the preset gray threshold value as an abnormal pixel point;
determining a region to be processed by taking the abnormal pixel point as a circle center and a preset distance as a radius; determining a first pixel point and a second pixel point in a region to be processed; the first pixel point is the pixel point with the largest difference value between the gray value in the area to be processed and the gray value of the abnormal pixel point; the first pixel point is a pixel point with the minimum difference value between the gray value in the region to be processed and the gray value of the abnormal pixel point;
determining a first distance value between the abnormal pixel point and the first pixel point and a second distance value between the abnormal pixel point and the second pixel point;
inquiring a preset first distance value-second distance value-noise reduction parameter data table according to the first distance value and the second distance value, determining a target noise reduction parameter, and performing noise reduction treatment on the region to be treated based on the target noise reduction parameter to obtain a noise-reduced monitoring image.
6. The intelligent access control theft-prevention system based on wireless network of claim 1, further comprising: the vibration sensing module is used for detecting a vibration signal of the access control body and converting the vibration signal into a vibration value; and when the vibration value is determined to be larger than the preset vibration value, sending out an alarm prompt.
7. The intelligent access control theft-prevention system based on wireless network of claim 1, further comprising: the detection module is used for detecting the current signal on the door lock control module and collecting signal waves of the current signal based on a preset sampling rate in a preset time period;
Dividing the signal wave into M sections of sub-signal waves, wherein the time length of each section of sub-signal wave is N milliseconds;
Acquiring sampling values of all sampling points of the sub-signal wave before N/2 milliseconds, and determining a maximum sampling value; taking the sub-signal wave with the maximum sampling value smaller than the preset threshold value as an abnormal sub-signal wave, and removing the abnormal sub-signal wave; obtaining a target current signal according to the sub-signal wave with the maximum sampling value being greater than or equal to a preset threshold value;
And extracting the characteristics of the target current signal, determining the current characteristics, comparing the current characteristics with preset current characteristics, and sending out an alarm prompt when the current characteristics are inconsistent with the preset current characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311164797.4A CN117292465B (en) | 2023-09-07 | 2023-09-07 | Intelligent access control anti-theft system based on wireless network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311164797.4A CN117292465B (en) | 2023-09-07 | 2023-09-07 | Intelligent access control anti-theft system based on wireless network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117292465A CN117292465A (en) | 2023-12-26 |
| CN117292465B true CN117292465B (en) | 2024-08-02 |
Family
ID=89250926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311164797.4A Active CN117292465B (en) | 2023-09-07 | 2023-09-07 | Intelligent access control anti-theft system based on wireless network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117292465B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694353A (en) * | 2017-04-10 | 2018-10-23 | 上海聚虹光电科技有限公司 | A kind of multi-modal personal identification method of recognition of face and iris recognition |
| CN108876998A (en) * | 2018-06-13 | 2018-11-23 | 上海快鱼电子有限公司 | Gate inhibition's method and system of testimony of a witness unification based on living things feature recognition |
| CN109326009A (en) * | 2017-08-01 | 2019-02-12 | 深圳市永达电子信息股份有限公司 | A kind of system and method that speeds passage through customs based on recognition of face |
| CN110675433A (en) * | 2019-10-31 | 2020-01-10 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101179294B (en) * | 2006-11-09 | 2012-07-04 | 黄山好视达通信技术有限公司 | Self-adaptive echo eliminator and echo eliminating method thereof |
| CN212160784U (en) * | 2019-12-31 | 2020-12-15 | 深圳阜时科技有限公司 | Identity recognition device and entrance guard equipment |
| KR20220168951A (en) * | 2021-06-16 | 2022-12-26 | 센스타임 인터내셔널 피티이. 리미티드. | Methods, devices, devices and storage media for associating subject information |
| CN116612776A (en) * | 2022-02-08 | 2023-08-18 | 中移系统集成有限公司 | Signal processing method and device for microphone array |
-
2023
- 2023-09-07 CN CN202311164797.4A patent/CN117292465B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694353A (en) * | 2017-04-10 | 2018-10-23 | 上海聚虹光电科技有限公司 | A kind of multi-modal personal identification method of recognition of face and iris recognition |
| CN109326009A (en) * | 2017-08-01 | 2019-02-12 | 深圳市永达电子信息股份有限公司 | A kind of system and method that speeds passage through customs based on recognition of face |
| CN108876998A (en) * | 2018-06-13 | 2018-11-23 | 上海快鱼电子有限公司 | Gate inhibition's method and system of testimony of a witness unification based on living things feature recognition |
| CN110675433A (en) * | 2019-10-31 | 2020-01-10 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117292465A (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111881726B (en) | Living body detection method and device and storage medium | |
| CN105868613A (en) | Biometric feature recognition method, biometric feature recognition device and mobile terminal | |
| CN105989836B (en) | Voice acquisition method and device and terminal equipment | |
| CN104851140A (en) | Face recognition-based attendance access control system | |
| CN104700018B (en) | A kind of recognition methods for intelligent robot | |
| CN107293301B (en) | Recognition methods and system based on dental articulation sound | |
| CN102254188A (en) | Palmprint recognizing method and device | |
| Nait-Ali | Hidden biometrics: Towards using biosignals and biomedical images for security applications | |
| Hentati et al. | Development a new algorithm for iris biometric recognition | |
| CN111062021A (en) | Method and device for identity authentication based on wearable equipment | |
| Vega et al. | Biometric personal identification system based on patterns created by finger veins | |
| CN110069965A (en) | A kind of robot personal identification method | |
| CN109377601B (en) | Intelligent office access control system based on fingerprint identification | |
| Amritha et al. | Matcher performance-based score level fusion schemes for multi-modal biometric authentication system | |
| CN117292465B (en) | Intelligent access control anti-theft system based on wireless network | |
| CN109145845B (en) | Residence authority electronic distinguishing method | |
| Ives et al. | Iris recognition using the ridge energy direction (RED) algorithm | |
| CN110598522A (en) | Identity comparison method based on face and palm print palm vein recognition | |
| Patel et al. | Human identification by partial iris segmentation using pupil circle growing based on binary integrated edge intensity curve | |
| KR100374695B1 (en) | Automatic Fingerprint Identification System using Direct Ridge Extraction | |
| Maddala et al. | Implementation and evaluation of NIST Biometric Image Software for fingerprint recognition | |
| CN111325118A (en) | Method for identity authentication based on video and video equipment | |
| Sathish et al. | Personal authentication system using hand vein biometric | |
| CN109919050A (en) | Identity recognition method and device | |
| Lokhande et al. | Wavelet packet based iris texture analysis for person authentication |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |