Papers by Hamid R. Tizhoosh
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.
Choquet integral-based aggregation of image template matching algorithms
22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003, 2000
ABSTRACT
Additive fuzzy enhancement and an associative memory for feature tracking in radiation therapy images
Proceedings of International Conference on Image Processing, 2000
ABSTRACT
2006 IEEE International Conference on Evolutionary Computation, 2000
Evolutionary Algorithms (EAs) are well-known optimization approaches to cope with non-linear, com... more Evolutionary Algorithms (EAs) are well-known optimization approaches to cope with non-linear, complex problems. These population-based algorithms, however, suffer from a general weakness; they are computationally expensive due to slow nature of the evolutionary process. This paper presents some novel schemes to accelerate convergence of evolutionary algorithms. The proposed schemes employ opposition-based learning for population initialization and also for generation jumping. In order to investigate the performance of the proposed schemes, Differential Evolution (DE), an efficient and robust optimization method, has been used. The main idea is general and applicable to other population-based algorithms such as Genetic algorithms, Swarm Intelligence, and Ant Colonies. A set of test functions including unimodal and multimodal benchmark functions is employed for experimental verification. The details of proposed schemes and also conducted experiments are given. The results are highly promising.
Observer-dependent sharpening
Proceedings. International Conference on Image Processing, 2000
ABSTRACT
Observer-Dependent Image Enhancement
Studies in Fuzziness and Soft Computing, 2003
Studies in Fuzziness and Soft Computing, 2003
Über Binarisierung und Potentiale der Fuzzy-Ansätze
Informatik aktuell, 1998
Oppositional Concepts in Computational Intelligence
... 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..... ...
IRIS Segmentation: Detecting Pupil, Limbus and Eyelids
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 ...
Q(lambda)-Based Image Thresholding
Crv, 2004
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
System and Method for Image Segmentation
Filter fusion for image enhancement using reinforcement learning
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 ...
Studies in Computational Intelligence
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.
Reinforcement learning is a machine intelligence scheme for learning in highly dynamic and probab... more Reinforcement learning is a machine intelligence scheme for learning in highly dynamic and probabilistic environments. The methodology, however, suffers from a major drawback; the convergence to an optimal solution usually requires high computational expense since all states should be visited frequently in order to guarantee a reliable policy. In this paper, a new reinforcement learning algorithm is introduced to achieve a faster convergence by taking into account the opposite actions. By considering the opposite actions simultaneously multiple updates can be made for each state observation. This leads to a shorter exploration period and, hence, expedites the convergence. Experimental results for the grid world problem of different sizes are provided to verify the performance of the proposed approach.
In recent years, many researchers have applied the fuzzy logic to develop new image processing al... more In recent years, many researchers have applied the fuzzy logic to develop new image processing algorithms. Meanwhile, the fuzzy image processing is one of the important application areas of fuzzy logic. This paper gives a brief overview of potentials of fuzzy techniques. The state of the art is described by referring to some practical examples.
Conference Record - IEEE Instrumentation and Measurement Technology Conference
In many image processing applications the image quality should be improved to support the human p... more In many image processing applications the image quality should be improved to support the human perception. The image quality evaluation by the human observers is, however, heavily subjective in the nature. Different observers judge the image quality differently. I n many cases the relevant part of image information which is perceived by the observer should reach n maximum. In this work we present a new approach to image enhancement which is based on fusion of different algorithms. We use fuzzy measure theory to represwt the human subjectivir'y, and fuzzy integrals to aggregate this subjectivity with objective criteria. We also apply the Dempster aggregation rule to define a degree of compromise. Findy, we use a fuzzy rule-based approach to construct an aggregation matrix that allow us to generate enhanced images for each individual observer. As an example, we apply this approach to increme the quality of portal images that are used in radiation therapy. consider the cast that three differrnt algorithms are applied to enhance the original input image.
Uploads
Papers by Hamid R. Tizhoosh