Depending on the purpose for which a medical image is taken, some areas of it contain more clinic... more Depending on the purpose for which a medical image is taken, some areas of it contain more clinical information than others. These areas are usually considered as regions of interest (ROI). The area outside the ROI is either the background or contains some clinical information with relative importance. In this paper we introduce two preprocessing and error-free compression routines. The first preprocessing routine, if applied to X-ray images, could result in a reconstructed image with a controllable amount of deterioration in its various areas. The second preprocessing routine is applied to X-ray CT, MR and radionuclide images prior to the compression. Its aim is to automatically detect the ROI and neglect the background. The background is replaced by an optional gray level when these images are being reconstructed. These routines were applied to a variety of medical images and relatively good compression ratios were obtained.
There is a big dierence between Simulation League and Middle Size League in RoboCup, that is, a p... more There is a big dierence between Simulation League and Middle Size League in RoboCup, that is, a program written for the former can not be easily transferred to the latter. Since the final aim is real robotics, in this paper we suggest a new match for RoboCup Soccer which can fill this gap. We designed and implemented a Modeled Robot
Self-Organization and Autonomous Systems in Computing and Communications, 2005
The main goal of any testbed is to facilitate the trial and evaluation of ideas that have promise... more The main goal of any testbed is to facilitate the trial and evaluation of ideas that have promise in the real world. In fact, in a real platform several phys- ical or hardware restrictions exist and maybe arise for an agent or robot. These restrictions affect the performance of implemented algorithms. To the best of our knowledge, at present, only
Canadian Conference on Electrical and Computer Engineering, 2005., 2005
... Mansour Jamzad Computer Engineering Department Sharif University of Technology Tehran,Iran em... more ... Mansour Jamzad Computer Engineering Department Sharif University of Technology Tehran,Iran email: jamzad@sharif ... Arvand robots are constructed by Sharif CE Middle size RoboCup ... Rover Navigation Software for Planetary Exploration," IEEE Aerospace Conference, ...
Proceedings of the 2003 IEEE International Symposium on Intelligent Control ISIC-03, 2003
One of the main challenges in RoboCup where a team of robots play soccer against another such tea... more One of the main challenges in RoboCup where a team of robots play soccer against another such team, is to maintain a high level of speed and accuracy in decision making and performing actions by the robot players. Although we might be able to use complicated hardware and software on the robots to achieve the desired accuracy, but such systems
ABSTRACT Different types of visual features provide multi-modal representation for images in the ... more ABSTRACT Different types of visual features provide multi-modal representation for images in the annotation task. Conventional graph-based image annotation methods integrate various features into a single descriptor and consider one node for each descriptor on the learning graph. However, this graph does not capture the information of individual features, making it unsuitable for propagating the labels of annotated images. In this paper, we address this issue by proposing an approach for fusing the visual features such that a specific subgraph is constructed for each visual modality and then subgraphs are connected to form a supergraph. As the size of supergraph grows linearly with the number of visual features, it is essential to handle large computational complexity of label propagation on the supergraph. To this end, we extract some prototypes from the feature vectors of images and incorporate them into the supergraph construction. The learning process is then conducted on the prototypes, instead of a large number of feature vectors, making the label inference scalable. The experiments on a wide range of standard datasets reveal that the proposed approach achieves scalable image annotation while having an acceptable level of performance.
2012 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2012
ABSTRACT Since tracking algorithms should be robust with respect to appearance changes, online al... more ABSTRACT Since tracking algorithms should be robust with respect to appearance changes, online algorithms has been investigated recently instead of offline ones which has shown an acceptable performance in controlled environments. The most challenging issue in online algorithms is updating of the model causing tracking failure because of introducing small errors in each update and disturbing the appearance model (drift). In this paper, we propose an online generative tracking algorithm in order to overcome the challenges such as occlusion, object shape changes, and illumination variations. In each frame, color distribution of target candidates is obtained and the candidate having the lowest distance to the object distribution is considered as the object. In addition, in our work, the particle filter structure is used in which the samples are weighted proportional to their distance to the model. The model which is a color distribution is updated using D2-clustring algorithm. The most distinctive features of our algorithm are: 1) Updating the model using D2-clustering, 2) Avoiding drifting by using the color distribution of the target in the first and last frame, and 3) Detecting of occlusion by considering distance between the model and the best candidate. Experimental results show that our tracker outperforms other algorithms in videos containing challenging scenarios.
2009 International Conference on Availability, Reliability and Security, 2009
Robustness against attacks is an important requirement in image watermarking. This paper presents... more Robustness against attacks is an important requirement in image watermarking. This paper presents a robust watermarking algorithm in wavelet transform domain. Firstly, original image is decomposed into its subbands using three level wavelet transform, then, significant coefficients with the same position in HL, LH and HH subbands of the last level are extracted to make a triplet. To embed a
This paper presents algorithms based on image processing for detecting internal blood spots and e... more This paper presents algorithms based on image processing for detecting internal blood spots and eggshell dirt by processing acquired images from eggs under different illuminations. The algorithm can also detect the severity of dirt on eggshell. In order to carry out image processing and extract useful features of captured images of eggs by machine vision we developed an algorithm in
ABSTRACT This paper presents a cover selection steganography method based on introduction of a te... more ABSTRACT This paper presents a cover selection steganography method based on introduction of a technique for computing steganography capacity as a property of images. An ensemble system that uses different steganalyzer units, determines the upper bound of embedding rate in a cover image. In this technique, each steganalyzer unit is a combination of multiple steganalyzers with a same type but each one trained to detect stego images with a certain payload. Our proposed method minimizes the risk of detection by selecting a proper cover image that its steganography capacity is sufficient to hide a specific secret data securely. Experimental results demonstrate the efficiency and practicability of the proposed technique in enhancing the security of stego images.
2008 IEEE 8th International Conference on Computer and Information Technology Workshops, 2008
... indices (location addresses) in DCT coefficients of host image as suggested in [9]. Our appro... more ... indices (location addresses) in DCT coefficients of host image as suggested in [9]. Our approach aims to reduce the risk of detection, while keeping a ... [9] Z. Kermani, M. Jamzad, A Robust Steganography Algorithm ... [18] K. Cho, J. Jang, K. Hong, Adaptive skin-color filter, Pattern ...
Depending on the purpose for which a medical image is taken, some areas of it contain more clinic... more Depending on the purpose for which a medical image is taken, some areas of it contain more clinical information than others. These areas are usually considered as regions of interest (ROI). The area outside the ROI is either the background or contains some clinical information with relative importance. In this paper we introduce two preprocessing and error-free compression routines. The first preprocessing routine, if applied to X-ray images, could result in a reconstructed image with a controllable amount of deterioration in its various areas. The second preprocessing routine is applied to X-ray CT, MR and radionuclide images prior to the compression. Its aim is to automatically detect the ROI and neglect the background. The background is replaced by an optional gray level when these images are being reconstructed. These routines were applied to a variety of medical images and relatively good compression ratios were obtained.
There is a big dierence between Simulation League and Middle Size League in RoboCup, that is, a p... more There is a big dierence between Simulation League and Middle Size League in RoboCup, that is, a program written for the former can not be easily transferred to the latter. Since the final aim is real robotics, in this paper we suggest a new match for RoboCup Soccer which can fill this gap. We designed and implemented a Modeled Robot
Self-Organization and Autonomous Systems in Computing and Communications, 2005
The main goal of any testbed is to facilitate the trial and evaluation of ideas that have promise... more The main goal of any testbed is to facilitate the trial and evaluation of ideas that have promise in the real world. In fact, in a real platform several phys- ical or hardware restrictions exist and maybe arise for an agent or robot. These restrictions affect the performance of implemented algorithms. To the best of our knowledge, at present, only
Canadian Conference on Electrical and Computer Engineering, 2005., 2005
... Mansour Jamzad Computer Engineering Department Sharif University of Technology Tehran,Iran em... more ... Mansour Jamzad Computer Engineering Department Sharif University of Technology Tehran,Iran email: jamzad@sharif ... Arvand robots are constructed by Sharif CE Middle size RoboCup ... Rover Navigation Software for Planetary Exploration," IEEE Aerospace Conference, ...
Proceedings of the 2003 IEEE International Symposium on Intelligent Control ISIC-03, 2003
One of the main challenges in RoboCup where a team of robots play soccer against another such tea... more One of the main challenges in RoboCup where a team of robots play soccer against another such team, is to maintain a high level of speed and accuracy in decision making and performing actions by the robot players. Although we might be able to use complicated hardware and software on the robots to achieve the desired accuracy, but such systems
ABSTRACT Different types of visual features provide multi-modal representation for images in the ... more ABSTRACT Different types of visual features provide multi-modal representation for images in the annotation task. Conventional graph-based image annotation methods integrate various features into a single descriptor and consider one node for each descriptor on the learning graph. However, this graph does not capture the information of individual features, making it unsuitable for propagating the labels of annotated images. In this paper, we address this issue by proposing an approach for fusing the visual features such that a specific subgraph is constructed for each visual modality and then subgraphs are connected to form a supergraph. As the size of supergraph grows linearly with the number of visual features, it is essential to handle large computational complexity of label propagation on the supergraph. To this end, we extract some prototypes from the feature vectors of images and incorporate them into the supergraph construction. The learning process is then conducted on the prototypes, instead of a large number of feature vectors, making the label inference scalable. The experiments on a wide range of standard datasets reveal that the proposed approach achieves scalable image annotation while having an acceptable level of performance.
2012 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2012
ABSTRACT Since tracking algorithms should be robust with respect to appearance changes, online al... more ABSTRACT Since tracking algorithms should be robust with respect to appearance changes, online algorithms has been investigated recently instead of offline ones which has shown an acceptable performance in controlled environments. The most challenging issue in online algorithms is updating of the model causing tracking failure because of introducing small errors in each update and disturbing the appearance model (drift). In this paper, we propose an online generative tracking algorithm in order to overcome the challenges such as occlusion, object shape changes, and illumination variations. In each frame, color distribution of target candidates is obtained and the candidate having the lowest distance to the object distribution is considered as the object. In addition, in our work, the particle filter structure is used in which the samples are weighted proportional to their distance to the model. The model which is a color distribution is updated using D2-clustring algorithm. The most distinctive features of our algorithm are: 1) Updating the model using D2-clustering, 2) Avoiding drifting by using the color distribution of the target in the first and last frame, and 3) Detecting of occlusion by considering distance between the model and the best candidate. Experimental results show that our tracker outperforms other algorithms in videos containing challenging scenarios.
2009 International Conference on Availability, Reliability and Security, 2009
Robustness against attacks is an important requirement in image watermarking. This paper presents... more Robustness against attacks is an important requirement in image watermarking. This paper presents a robust watermarking algorithm in wavelet transform domain. Firstly, original image is decomposed into its subbands using three level wavelet transform, then, significant coefficients with the same position in HL, LH and HH subbands of the last level are extracted to make a triplet. To embed a
This paper presents algorithms based on image processing for detecting internal blood spots and e... more This paper presents algorithms based on image processing for detecting internal blood spots and eggshell dirt by processing acquired images from eggs under different illuminations. The algorithm can also detect the severity of dirt on eggshell. In order to carry out image processing and extract useful features of captured images of eggs by machine vision we developed an algorithm in
ABSTRACT This paper presents a cover selection steganography method based on introduction of a te... more ABSTRACT This paper presents a cover selection steganography method based on introduction of a technique for computing steganography capacity as a property of images. An ensemble system that uses different steganalyzer units, determines the upper bound of embedding rate in a cover image. In this technique, each steganalyzer unit is a combination of multiple steganalyzers with a same type but each one trained to detect stego images with a certain payload. Our proposed method minimizes the risk of detection by selecting a proper cover image that its steganography capacity is sufficient to hide a specific secret data securely. Experimental results demonstrate the efficiency and practicability of the proposed technique in enhancing the security of stego images.
2008 IEEE 8th International Conference on Computer and Information Technology Workshops, 2008
... indices (location addresses) in DCT coefficients of host image as suggested in [9]. Our appro... more ... indices (location addresses) in DCT coefficients of host image as suggested in [9]. Our approach aims to reduce the risk of detection, while keeping a ... [9] Z. Kermani, M. Jamzad, A Robust Steganography Algorithm ... [18] K. Cho, J. Jang, K. Hong, Adaptive skin-color filter, Pattern ...
Uploads
Papers by Mansour Jamzad