With the availability of whole-slide imaging in pathology, high-resolution images offer a more co... more With the availability of whole-slide imaging in pathology, high-resolution images offer a more convenient disease observation but also require content-based retrieval of large scans. The bag-of-visual-words methodology has shown a high ability to describe the image content for recognition and retrieval purposes. In this work, a variant of the bag-of-visual-words with multiple dictionaries for histopathology image classification is proposed and tested on the image dataset Kimia Path24 with more than 27,000 patches of size 1000 × 1000 belonging to 24 different classes. Features are extracted from patches and clustered to form multiple codebooks. The histo-gram intersection approach and support vector machines are exploited to build multiple classifiers. At last, the majority voting determines the final classification for each patch. The experiments demonstrate the superiority of the proposed method for histopathology images that surpasses deep networks, LBP and other BoW results.
With the availability of whole-slide imaging in pathology, high-resolution images offer a more co... more With the availability of whole-slide imaging in pathology, high-resolution images offer a more convenient disease observation but also require content-based retrieval of large scans. The bag-of-visual-words methodology has shown a high ability to describe the image content for recognition and retrieval purposes. In this work, a variant of the bag-of-visual-words with multiple dictionaries for histopathology image classification is proposed and tested on the image dataset Kimia Path24 with more than 27,000 patches of size 1000 × 1000 belonging to 24 different classes. Features are extracted from patches and clustered to form multiple codebooks. The histo-gram intersection approach and support vector machines are exploited to build multiple classifiers. At last, the majority voting determines the final classification for each patch. The experiments demonstrate the superiority of the proposed method for histopathology images that surpasses deep networks, LBP and other BoW results.
... 140. Nadia Magnenat-Thalmann, Lakhmi C. Jain and N. Ichalkaranje (Eds.) New Advances in Virtu... more ... 140. Nadia Magnenat-Thalmann, Lakhmi C. Jain and N. Ichalkaranje (Eds.) New Advances in Virtual Humans, 2008 ISBN 978-3-540-79867-5 Vol. 141. ... 287 14 Opposition Mining in Reservoir Management Masoud Mahootchi, HR Tizhoosh, Kumaraswamy Ponnambalam..... ...
Proceedings Icip International Conference on Image Processing, Oct 1, 2006
This paper presents an active contour model to accurately de-tect pupil boundary in order to impr... more This paper presents an active contour model to accurately de-tect pupil boundary in order to improve the performance of iris recognition systems. The contour model takes into con-sideration that an actual pupil boundary is a near-circular con-tour rather than a perfect circle. Two ...
One of the problems in image pro- cessing is finding an appropriate threshold in order to convert... more One of the problems in image pro- cessing is finding an appropriate threshold in order to convert an image to a binary one. In this paper we introduce a new method for image thresholding. We use reinforcement learning as an effective way to find the optimal threshold. Q(λ) is implemented as a learning algorithm to achieve more accurate results. The
CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436), 2003
In many applications different sorts of noise conupt images. In most cases if one filter is used ... more In many applications different sorts of noise conupt images. In most cases if one filter is used for the whole image, the result is usually unsatisfactory. For instance, a filter, which can suppress noise, may also eliminate significant image details. Filter fusion is an approach to ...
Although the concept of the opposition has an old history in other fields and sciences, this is t... more Although the concept of the opposition has an old history in other fields and sciences, this is the first time that it contributes to enhance an optimizer. This chapter presents a novel scheme to make the differential evolution (DE) algorithm faster. The proposed opposition-based DE (ODE) employs opposition-based optimization (OBO) for population initialization and also for generation jumping. In this work, opposite numbers have been utilized to improve the convergence rate of the classical DE. A test suite with 15 benchmark functions is employed for experimental verification. The contribution of the opposite numbers is empirically verified. Additionally, two time varying models for control parameter adjustment of ODE are investigated. Details of the ODE algorithm, the test set, and the comparison strategy are provided.
With the availability of whole-slide imaging in pathology, high-resolution images offer a more co... more With the availability of whole-slide imaging in pathology, high-resolution images offer a more convenient disease observation but also require content-based retrieval of large scans. The bag-of-visual-words methodology has shown a high ability to describe the image content for recognition and retrieval purposes. In this work, a variant of the bag-of-visual-words with multiple dictionaries for histopathology image classification is proposed and tested on the image dataset Kimia Path24 with more than 27,000 patches of size 1000 × 1000 belonging to 24 different classes. Features are extracted from patches and clustered to form multiple codebooks. The histo-gram intersection approach and support vector machines are exploited to build multiple classifiers. At last, the majority voting determines the final classification for each patch. The experiments demonstrate the superiority of the proposed method for histopathology images that surpasses deep networks, LBP and other BoW results.
With the availability of whole-slide imaging in pathology, high-resolution images offer a more co... more With the availability of whole-slide imaging in pathology, high-resolution images offer a more convenient disease observation but also require content-based retrieval of large scans. The bag-of-visual-words methodology has shown a high ability to describe the image content for recognition and retrieval purposes. In this work, a variant of the bag-of-visual-words with multiple dictionaries for histopathology image classification is proposed and tested on the image dataset Kimia Path24 with more than 27,000 patches of size 1000 × 1000 belonging to 24 different classes. Features are extracted from patches and clustered to form multiple codebooks. The histo-gram intersection approach and support vector machines are exploited to build multiple classifiers. At last, the majority voting determines the final classification for each patch. The experiments demonstrate the superiority of the proposed method for histopathology images that surpasses deep networks, LBP and other BoW results.
... 140. Nadia Magnenat-Thalmann, Lakhmi C. Jain and N. Ichalkaranje (Eds.) New Advances in Virtu... more ... 140. Nadia Magnenat-Thalmann, Lakhmi C. Jain and N. Ichalkaranje (Eds.) New Advances in Virtual Humans, 2008 ISBN 978-3-540-79867-5 Vol. 141. ... 287 14 Opposition Mining in Reservoir Management Masoud Mahootchi, HR Tizhoosh, Kumaraswamy Ponnambalam..... ...
Proceedings Icip International Conference on Image Processing, Oct 1, 2006
This paper presents an active contour model to accurately de-tect pupil boundary in order to impr... more This paper presents an active contour model to accurately de-tect pupil boundary in order to improve the performance of iris recognition systems. The contour model takes into con-sideration that an actual pupil boundary is a near-circular con-tour rather than a perfect circle. Two ...
One of the problems in image pro- cessing is finding an appropriate threshold in order to convert... more One of the problems in image pro- cessing is finding an appropriate threshold in order to convert an image to a binary one. In this paper we introduce a new method for image thresholding. We use reinforcement learning as an effective way to find the optimal threshold. Q(λ) is implemented as a learning algorithm to achieve more accurate results. The
CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436), 2003
In many applications different sorts of noise conupt images. In most cases if one filter is used ... more In many applications different sorts of noise conupt images. In most cases if one filter is used for the whole image, the result is usually unsatisfactory. For instance, a filter, which can suppress noise, may also eliminate significant image details. Filter fusion is an approach to ...
Although the concept of the opposition has an old history in other fields and sciences, this is t... more Although the concept of the opposition has an old history in other fields and sciences, this is the first time that it contributes to enhance an optimizer. This chapter presents a novel scheme to make the differential evolution (DE) algorithm faster. The proposed opposition-based DE (ODE) employs opposition-based optimization (OBO) for population initialization and also for generation jumping. In this work, opposite numbers have been utilized to improve the convergence rate of the classical DE. A test suite with 15 benchmark functions is employed for experimental verification. The contribution of the opposite numbers is empirically verified. Additionally, two time varying models for control parameter adjustment of ODE are investigated. Details of the ODE algorithm, the test set, and the comparison strategy are provided.
Uploads
Papers