Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586734
Thomas Penne, C. Tilmant, T. Chateau, V. Barra
Object Tracking is a very important domain in computer vision. It was recently approached using classification techniques and still more recently using boosting methods. Boosting is a general method of producing an accurate prediction rule by combining rough and moderately inaccurate ones. We introduce in this paper a modular object tracking algorithm based on one of these boosting methods: Adaboost. Tracking is performed on homogeneous feature spaces and the final classification decision is obtained by combining the decisions made on each of these spaces. A classifier update stage is also introduced, that allows the method both to handle time-varying objects in real-time (using fast computable features) and to handle partial occlusions. We compare the performance of our algorithm with Ensemble Tracking algorithm [2] on several real video sequences.
{"title":"Modular Ensemble Tracking","authors":"Thomas Penne, C. Tilmant, T. Chateau, V. Barra","doi":"10.1109/IPTA.2010.5586734","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586734","url":null,"abstract":"Object Tracking is a very important domain in computer vision. It was recently approached using classification techniques and still more recently using boosting methods. Boosting is a general method of producing an accurate prediction rule by combining rough and moderately inaccurate ones. We introduce in this paper a modular object tracking algorithm based on one of these boosting methods: Adaboost. Tracking is performed on homogeneous feature spaces and the final classification decision is obtained by combining the decisions made on each of these spaces. A classifier update stage is also introduced, that allows the method both to handle time-varying objects in real-time (using fast computable features) and to handle partial occlusions. We compare the performance of our algorithm with Ensemble Tracking algorithm [2] on several real video sequences.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586806
Nicolas Widynski, Séverine Dubuisson, I. Bloch
Dynamics modeling is of primal interest to track objects using particle filters. Even the choice of a well fitted noise parameter may lead to unsuccessful tracking when unexpected events arise, such as outliers, occultations, dynamics discontinuites… In this paper, we propose to introduce structural spatial information in particle filters. This information, expressed as spatial relations such as orientation or distance, is modeled in a fuzzy set framework, and is introduced in the dynamics in order to model the potential changes from one instant to the next one. The fuzzy modeling provides flexibility both in the semantics of the relations and in the transitions from one relation to another one. We show in our experiments that this kind of modeling is really adaptive to unexpected changes of dynamics, and outperforms classical filtering techniques while using only a small number of particles.
{"title":"Particle filtering with fuzzy spatial relations for object tracking","authors":"Nicolas Widynski, Séverine Dubuisson, I. Bloch","doi":"10.1109/IPTA.2010.5586806","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586806","url":null,"abstract":"Dynamics modeling is of primal interest to track objects using particle filters. Even the choice of a well fitted noise parameter may lead to unsuccessful tracking when unexpected events arise, such as outliers, occultations, dynamics discontinuites… In this paper, we propose to introduce structural spatial information in particle filters. This information, expressed as spatial relations such as orientation or distance, is modeled in a fuzzy set framework, and is introduced in the dynamics in order to model the potential changes from one instant to the next one. The fuzzy modeling provides flexibility both in the semantics of the relations and in the transitions from one relation to another one. We show in our experiments that this kind of modeling is really adaptive to unexpected changes of dynamics, and outperforms classical filtering techniques while using only a small number of particles.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"1999 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123551757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586780
Hamed Ghodrati, M. J. Dehghani, M. Helfroush, K. Kazemi
Iris segmentation, including localization and noise removal, is a fundamental step in iris recognition systems as the performance of the system is highly depend on this step. The aim of localization is to detect inner (pupil) and outer (limbic) boundaries. Noise removal consists of eliminating eyelids and eyelashes from localized image. In this paper, we propose a new localization algorithm, in which, unlike the previously reported works, no assumption for the shape of the boundaries is supposed. Inner boundary is localized by use of a coarse-to-fine strategy. In so doing, a set of morphological operators and canny edge detector are applied to the square region, which surrounds the pupil. Outer boundary is divided into right and left sides in which they are detected by arched Hough transform and finally merged together. The proposed algorithm is tested on the CASIA and MMU databases and the localized image is evaluated using the ground truth method. The obtained results indicate that our algorithm improves the precision of the iris localization.
{"title":"Localization of noncircular iris boundaries using morphology and arched Hough transform","authors":"Hamed Ghodrati, M. J. Dehghani, M. Helfroush, K. Kazemi","doi":"10.1109/IPTA.2010.5586780","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586780","url":null,"abstract":"Iris segmentation, including localization and noise removal, is a fundamental step in iris recognition systems as the performance of the system is highly depend on this step. The aim of localization is to detect inner (pupil) and outer (limbic) boundaries. Noise removal consists of eliminating eyelids and eyelashes from localized image. In this paper, we propose a new localization algorithm, in which, unlike the previously reported works, no assumption for the shape of the boundaries is supposed. Inner boundary is localized by use of a coarse-to-fine strategy. In so doing, a set of morphological operators and canny edge detector are applied to the square region, which surrounds the pupil. Outer boundary is divided into right and left sides in which they are detected by arched Hough transform and finally merged together. The proposed algorithm is tested on the CASIA and MMU databases and the localized image is evaluated using the ground truth method. The obtained results indicate that our algorithm improves the precision of the iris localization.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122274490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586735
J. Valantinas, D. Kancelkis
In this paper, a novel scheme for the accelerated analysis of quad-trees in the discrete wavelet spectrum of a digital image is proposed. During the pre-scanning step, the proposed scheme generates objective and specially structured binary codes for the whole set of quad-tree roots (wavelet coefficients) and thereby accumulates facts on the significance of respective descendants (wavelet coefficients comprising quad-trees on the view). The developed scheme can be successfully applied to any zero-tree based image coding procedure, such as the embedded zero-tree wavelet (EZW) algorithm of Shapiro and set partitioning in hierarchical trees (SPIHT) by Said and Pearlman. Exceptionally high performance of the proposed quad-tree analysis scheme, in the sense of image encoding times, is demonstrated using the EZW algorithm and the discrete Le Gall wavelet transform.
{"title":"Improving compression time in zero-tree based image coding procedures","authors":"J. Valantinas, D. Kancelkis","doi":"10.1109/IPTA.2010.5586735","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586735","url":null,"abstract":"In this paper, a novel scheme for the accelerated analysis of quad-trees in the discrete wavelet spectrum of a digital image is proposed. During the pre-scanning step, the proposed scheme generates objective and specially structured binary codes for the whole set of quad-tree roots (wavelet coefficients) and thereby accumulates facts on the significance of respective descendants (wavelet coefficients comprising quad-trees on the view). The developed scheme can be successfully applied to any zero-tree based image coding procedure, such as the embedded zero-tree wavelet (EZW) algorithm of Shapiro and set partitioning in hierarchical trees (SPIHT) by Said and Pearlman. Exceptionally high performance of the proposed quad-tree analysis scheme, in the sense of image encoding times, is demonstrated using the EZW algorithm and the discrete Le Gall wavelet transform.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125026096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586807
Xiyan He, P. Beauseroy, A. Smolarz
This paper presents a feature subspaces selection method which uses an ensemble of one-class SVMs. The objective is to improve or preserve the performance of a decision system in the presence of noise, loss of information or feature non-stationarity. The proposed method consists in first generating an ensemble of feature subspaces from the initial full-dimensional space, and then making the decision by using only the subspaces which are supposed to be immune to the non-stationary disturbance. One particularity of this method is that we use the one-class SVM ensemble to carry out the feature selection and the classification tasks at the same time. Textured image segmentation constitutes an appropriate application for the evaluation of the proposed approach. The experimental results demonstrate the effectiveness of the decision system that we have developed.
{"title":"Feature subspaces selection via one-class SVM: Application to textured image segmentation","authors":"Xiyan He, P. Beauseroy, A. Smolarz","doi":"10.1109/IPTA.2010.5586807","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586807","url":null,"abstract":"This paper presents a feature subspaces selection method which uses an ensemble of one-class SVMs. The objective is to improve or preserve the performance of a decision system in the presence of noise, loss of information or feature non-stationarity. The proposed method consists in first generating an ensemble of feature subspaces from the initial full-dimensional space, and then making the decision by using only the subspaces which are supposed to be immune to the non-stationary disturbance. One particularity of this method is that we use the one-class SVM ensemble to carry out the feature selection and the classification tasks at the same time. Textured image segmentation constitutes an appropriate application for the evaluation of the proposed approach. The experimental results demonstrate the effectiveness of the decision system that we have developed.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130258593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586831
M. Gabbouj
Particle swarm optimization (PSO) was introduced by Kennedy and Eberhart in 1995 [1] as a population based stochastic search and optimization process. The natural behavior of a bird flock when searching for food is simulated through the movements of the individuals (particles or living organisms) in the flock. The goal is to converge to the global optimum of some multi-dimensional function. PSO is conceptually related to other evolutionary algorithms such as Genetic Algorithms, Genetic Programming, Evolution Strategies, and Evolutionary Programming.
{"title":"Multidimensional particle swarm optimization and applications in data clustering and image retrieval","authors":"M. Gabbouj","doi":"10.1109/IPTA.2010.5586831","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586831","url":null,"abstract":"Particle swarm optimization (PSO) was introduced by Kennedy and Eberhart in 1995 [1] as a population based stochastic search and optimization process. The natural behavior of a bird flock when searching for food is simulated through the movements of the individuals (particles or living organisms) in the flock. The goal is to converge to the global optimum of some multi-dimensional function. PSO is conceptually related to other evolutionary algorithms such as Genetic Algorithms, Genetic Programming, Evolution Strategies, and Evolutionary Programming.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127663627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586770
A. Yúfera, Estefania Gallego
This paper presents a computer tool for automatic analysis of cell culture images. The program allows the extraction of relevant information from biological images for pre and post system analysis. In particular, this tool is being used for electrical characterization of electrode-solution-cell systems in which bio-impedance is the main parameter to be known. The correct modeling of this kind of systems enables both electronic system characterization for circuit design specifications and data decoding from measurements. The developed program can be used in cell culture image processing for geographic information extraction and sensor sizing, generating cell count and Analog Hardware Description Language (AHDL) equivalent circuits useful for whole system electrical simulations.
{"title":"Automatic generation of Analog Hardware Description Language (AHDL) code from cell culture images","authors":"A. Yúfera, Estefania Gallego","doi":"10.1109/IPTA.2010.5586770","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586770","url":null,"abstract":"This paper presents a computer tool for automatic analysis of cell culture images. The program allows the extraction of relevant information from biological images for pre and post system analysis. In particular, this tool is being used for electrical characterization of electrode-solution-cell systems in which bio-impedance is the main parameter to be known. The correct modeling of this kind of systems enables both electronic system characterization for circuit design specifications and data decoding from measurements. The developed program can be used in cell culture image processing for geographic information extraction and sensor sizing, generating cell count and Analog Hardware Description Language (AHDL) equivalent circuits useful for whole system electrical simulations.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132513197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586829
M. Mallem
Like Virtual Reality (VR), Augmented Reality (AR) is becoming an emerging platform for many applications like, edutainment, audio-visual aids, museums, medical, industry… This keynote surveys the current state-of-the-art in Augmented Reality. It describes work performed in our research team and explains the issues and problems encountered when building Augmented Reality Systems. It summarizes the tradeoffs and approaches taken so far to overcome these problems and speculates on future directions
{"title":"Augmented Reality: Issues, trends and challenges","authors":"M. Mallem","doi":"10.1109/IPTA.2010.5586829","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586829","url":null,"abstract":"Like Virtual Reality (VR), Augmented Reality (AR) is becoming an emerging platform for many applications like, edutainment, audio-visual aids, museums, medical, industry… This keynote surveys the current state-of-the-art in Augmented Reality. It describes work performed in our research team and explains the issues and problems encountered when building Augmented Reality Systems. It summarizes the tradeoffs and approaches taken so far to overcome these problems and speculates on future directions","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128337865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586753
Chao Zhu, Huanzhang Fu, Charles-Edmond Bichot, E. Dellandréa, Liming Chen
Visual object recognition is one of the most challenging problems in computer vision, due to both inter-class and intra-class variations. The local appearance-based features, especially SIFT, have gained a big success in such a task because of their great discriminative power. In this paper, we propose to adopt two different kinds of feature to characterize different aspects of object. One is the Local Binary Pattern (LBP) operator which catches texture structure, while the other one is segment-based feature which catches geometric information. The experimental results on PASCAL VOC benchmarks show that the LBP operator can provide complementary information to SIFT, and segment-based feature is mainly effective to rigid objects, which means its usefulness is class-specific. We evaluated our features and approach by participating in PASCAL VOC Challenge 2009 for the very first attempt, and achieved decent results.
{"title":"Visual object recognition using local binary patterns and segment-based feature","authors":"Chao Zhu, Huanzhang Fu, Charles-Edmond Bichot, E. Dellandréa, Liming Chen","doi":"10.1109/IPTA.2010.5586753","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586753","url":null,"abstract":"Visual object recognition is one of the most challenging problems in computer vision, due to both inter-class and intra-class variations. The local appearance-based features, especially SIFT, have gained a big success in such a task because of their great discriminative power. In this paper, we propose to adopt two different kinds of feature to characterize different aspects of object. One is the Local Binary Pattern (LBP) operator which catches texture structure, while the other one is segment-based feature which catches geometric information. The experimental results on PASCAL VOC benchmarks show that the LBP operator can provide complementary information to SIFT, and segment-based feature is mainly effective to rigid objects, which means its usefulness is class-specific. We evaluated our features and approach by participating in PASCAL VOC Challenge 2009 for the very first attempt, and achieved decent results.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126368300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-07-07DOI: 10.1109/IPTA.2010.5586728
Salim Chebbo, Philippe Durieux, B. Pesquet-Popescu
This paper proposes a new method to evaluate the temporal impairments of compressed video signals. The proposed algorithm is block based; each block in a given frame is first classified as stable or in motion with respect to its co-located blocks in the previous and next frames. For each in-motion block, a motion estimation process is used to find its best match. Then the flickering estimation is conducted over a 3D window involving the current block and its temporally co-located or best matched blocks of the previous and next frames. The temporal quality is finally deduced from the flickering estimation. Simulation results show the efficacy of our algorithm.
{"title":"Objective evaluation of compressed video's temporal flickering","authors":"Salim Chebbo, Philippe Durieux, B. Pesquet-Popescu","doi":"10.1109/IPTA.2010.5586728","DOIUrl":"https://doi.org/10.1109/IPTA.2010.5586728","url":null,"abstract":"This paper proposes a new method to evaluate the temporal impairments of compressed video signals. The proposed algorithm is block based; each block in a given frame is first classified as stable or in motion with respect to its co-located blocks in the previous and next frames. For each in-motion block, a motion estimation process is used to find its best match. Then the flickering estimation is conducted over a 3D window involving the current block and its temporally co-located or best matched blocks of the previous and next frames. The temporal quality is finally deduced from the flickering estimation. Simulation results show the efficacy of our algorithm.","PeriodicalId":236574,"journal":{"name":"2010 2nd International Conference on Image Processing Theory, Tools and Applications","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123204282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：