Pub Date : 2005-10-24DOI: 10.1109/ISPA.2005.195432
Matej Perse, J. Pers, M. Kristan, S. Kovacic, G. Vuckovic
The paper deals with the problem of computer vision based multi-person motion tracking, which in many cases suffers from lack of discriminating features of observed persons. To solve this problem, a physics based model of human motion is proposed, which includes internal forces of the persons by the means of the Kalman filter, and the cylindrical envelopes, which produce collision avoiding forces when observed persons come to close proximity. We tested the proposed method on two sequences, one from squash match, and the other from the basketball play and found out that the number of tracker mistakes significantly decreased.
{"title":"Physics-based modelling of human motion using Kalman filter and collision avoidance algorithm","authors":"Matej Perse, J. Pers, M. Kristan, S. Kovacic, G. Vuckovic","doi":"10.1109/ISPA.2005.195432","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195432","url":null,"abstract":"The paper deals with the problem of computer vision based multi-person motion tracking, which in many cases suffers from lack of discriminating features of observed persons. To solve this problem, a physics based model of human motion is proposed, which includes internal forces of the persons by the means of the Kalman filter, and the cylindrical envelopes, which produce collision avoiding forces when observed persons come to close proximity. We tested the proposed method on two sequences, one from squash match, and the other from the basketball play and found out that the number of tracker mistakes significantly decreased.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"223 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488514","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195409
F. Yang, M. Paindavoine, H. Abdi
In this article, we present some development results of a system that performs mosaicing (or mosaicking) of panoramic faces. Our objective is to study the feasibility of panoramic face construction in real-time. To do so, we built a simple acquisition system composed of 5 standard cameras which, together, can take simultaneously 5 views of a face at different angles. Then, we chose an easily hardware-achievable algorithm, consisting of successive linear transformations, in order to compose a panoramic face from these 5 views. The method has been tested on a relatively large number of faces. In order to validate our system of panoramic face mosaicing, we also conducted a preliminary study on panoramic faces recognition, based on the principal component method. Experimental results show the feasibility and viability of our system.
{"title":"Fast panoramic face mosaicing and recognition","authors":"F. Yang, M. Paindavoine, H. Abdi","doi":"10.1109/ISPA.2005.195409","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195409","url":null,"abstract":"In this article, we present some development results of a system that performs mosaicing (or mosaicking) of panoramic faces. Our objective is to study the feasibility of panoramic face construction in real-time. To do so, we built a simple acquisition system composed of 5 standard cameras which, together, can take simultaneously 5 views of a face at different angles. Then, we chose an easily hardware-achievable algorithm, consisting of successive linear transformations, in order to compose a panoramic face from these 5 views. The method has been tested on a relatively large number of faces. In order to validate our system of panoramic face mosaicing, we also conducted a preliminary study on panoramic faces recognition, based on the principal component method. Experimental results show the feasibility and viability of our system.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122530194","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195417
F. Alonso-Fernandez, Julian Fierrez, F. del-Valle, J. Ortega-Garcia
On-line signature verification for Tablet PC devices is studied. The on-line signature verification algorithm presented by the authors at the First International Signature Verification Competition (SVC 2004) is adapted to work in Tablet PC environments. An example prototype of securing access and securing document application using this Tablet PC system is also reported. Two different commercial Tablet PCs are evaluated, including information of interest for signature verification systems such as sampling and pressure statistics. Authentication performance experiments are reported considering both random and skilled forgeries by using a new database with over 3000 signatures.
{"title":"On-line signature verification using Tablet PC","authors":"F. Alonso-Fernandez, Julian Fierrez, F. del-Valle, J. Ortega-Garcia","doi":"10.1109/ISPA.2005.195417","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195417","url":null,"abstract":"On-line signature verification for Tablet PC devices is studied. The on-line signature verification algorithm presented by the authors at the First International Signature Verification Competition (SVC 2004) is adapted to work in Tablet PC environments. An example prototype of securing access and securing document application using this Tablet PC system is also reported. Two different commercial Tablet PCs are evaluated, including information of interest for signature verification systems such as sampling and pressure statistics. Authentication performance experiments are reported considering both random and skilled forgeries by using a new database with over 3000 signatures.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129757104","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195424
N. Amor, N. Amara
Optical characters recognition (OCR) has been an active subject of research since the early days of Computers. Despite the age of the subject, it remains one of the most challenging and exciting areas of research in computer science. In recent years it has grown into a mature discipline, producing a huge body of work. Arabic character recognition has been one of the last major languages to receive attention. This is due, in part, to the cursive nature of the task since even printed Arabic characters are in cursive form. This paper describes the performance of combining Hough transform and hidden Markov models in a multifont Arabic OCR system. Experimental tests have been carried out on a set of 85,000 samples of characters corresponding to 5 different fonts from the most commonly used in Arabic writing. Some promising experimental results are reported.
{"title":"Multifont Arabic character recognition using Hough transform and hidden Markov models","authors":"N. Amor, N. Amara","doi":"10.1109/ISPA.2005.195424","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195424","url":null,"abstract":"Optical characters recognition (OCR) has been an active subject of research since the early days of Computers. Despite the age of the subject, it remains one of the most challenging and exciting areas of research in computer science. In recent years it has grown into a mature discipline, producing a huge body of work. Arabic character recognition has been one of the last major languages to receive attention. This is due, in part, to the cursive nature of the task since even printed Arabic characters are in cursive form. This paper describes the performance of combining Hough transform and hidden Markov models in a multifont Arabic OCR system. Experimental tests have been carried out on a set of 85,000 samples of characters corresponding to 5 different fonts from the most commonly used in Arabic writing. Some promising experimental results are reported.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128395669","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195456
D. Sawicki
The light point figure is an image of a source of light seen in the reflector surface of a headlight. The source location is one of decisive parameters that influence the shape of the figure. The paper is an attempt to estimate the source of light location on the basis of the shape of the light point figure. The location in the reflector focus was assumed as a standard position. The displacement along an optical axis and perpendicular axis was considered. A set of factors that describe the shape of the figure was introduced. Through using them the functional dependencies between source's displacement and shape of figure were defined. An algorithm for determining the source location (displacement in relation to standard position) was introduced. This algorithm uses proposed functional dependencies and nonlinear programming methods. The light point figure is calculated using ray tracing.
{"title":"Estimation of the light source position on the basis of the light point figure","authors":"D. Sawicki","doi":"10.1109/ISPA.2005.195456","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195456","url":null,"abstract":"The light point figure is an image of a source of light seen in the reflector surface of a headlight. The source location is one of decisive parameters that influence the shape of the figure. The paper is an attempt to estimate the source of light location on the basis of the shape of the light point figure. The location in the reflector focus was assumed as a standard position. The displacement along an optical axis and perpendicular axis was considered. A set of factors that describe the shape of the figure was introduced. Through using them the functional dependencies between source's displacement and shape of figure were defined. An algorithm for determining the source location (displacement in relation to standard position) was introduced. This algorithm uses proposed functional dependencies and nonlinear programming methods. The light point figure is calculated using ray tracing.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123362134","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195390
Zhang Xiao-guang, Gao Ding, Xu Jian-jian
Since radiographic testing weld image possesses several shortcomings, such as bad contrast ratio, narrow range of grayscale and fuzzy image, common enhancement method cannot improve contrast ratio and at the same time preserve edges well. Fuzzy enhancement does not modify pixel graylevel in the fuzzy feature space just like histogram and can obtain high-definition image output. In this paper, on the basis of analyzing disadvantages of traditional fuzzy enhancement algorithm a generalized fuzzy enhancement algorithm is put forward. This algorithm can map the image to the generalized fuzzy space through involving the concept of generalized fuzzy set. At the same time, subsection sine function is chosen as fuzzy membership. Using the characteristics of generalized fuzzy transition with big range, image can obtain satisfactory enhancement effect through processing the radiographic testing image with generalized fuzzy enhancement algorithm. And this paper also introduces the method of fuzzy entropy to evaluate the enhancement effect and analyze the characteristics of sine membership function and generalized fuzzy enhancement operator.
{"title":"Generalized fuzzy enhancement of image for radiographic testing weld","authors":"Zhang Xiao-guang, Gao Ding, Xu Jian-jian","doi":"10.1109/ISPA.2005.195390","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195390","url":null,"abstract":"Since radiographic testing weld image possesses several shortcomings, such as bad contrast ratio, narrow range of grayscale and fuzzy image, common enhancement method cannot improve contrast ratio and at the same time preserve edges well. Fuzzy enhancement does not modify pixel graylevel in the fuzzy feature space just like histogram and can obtain high-definition image output. In this paper, on the basis of analyzing disadvantages of traditional fuzzy enhancement algorithm a generalized fuzzy enhancement algorithm is put forward. This algorithm can map the image to the generalized fuzzy space through involving the concept of generalized fuzzy set. At the same time, subsection sine function is chosen as fuzzy membership. Using the characteristics of generalized fuzzy transition with big range, image can obtain satisfactory enhancement effect through processing the radiographic testing image with generalized fuzzy enhancement algorithm. And this paper also introduces the method of fuzzy entropy to evaluate the enhancement effect and analyze the characteristics of sine membership function and generalized fuzzy enhancement operator.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114323922","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195455
D. Cakmakov, E. Celakoska
Estimation of difference between curves (curve matching) is a useful and often necessary technique in many applications, including: pattern recognition, image object recognition, robotic applications, computational geometry, etc. In this paper, three methods for curve matching using turning functions are presented. While the first two, called plain and polygonal method, are based on a simple adaptation of the existing approaches, the third one, called penalty method, is a new one and tries to overcome some important problems from the first two. The advantages and essential problems of the proposed methods are also discussed. A number of examples are presented to show major differences among the methods and their potential usefulness.
{"title":"Shape matching of digital curves","authors":"D. Cakmakov, E. Celakoska","doi":"10.1109/ISPA.2005.195455","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195455","url":null,"abstract":"Estimation of difference between curves (curve matching) is a useful and often necessary technique in many applications, including: pattern recognition, image object recognition, robotic applications, computational geometry, etc. In this paper, three methods for curve matching using turning functions are presented. While the first two, called plain and polygonal method, are based on a simple adaptation of the existing approaches, the third one, called penalty method, is a new one and tries to overcome some important problems from the first two. The advantages and essential problems of the proposed methods are also discussed. A number of examples are presented to show major differences among the methods and their potential usefulness.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134229419","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195413
J. Darbon
This paper sheds new light on minimization of the total variation under the L/sup 1/-norm as data fidelity term (L/sup 1/ +TV) and its link with mathematical morphology. It is well known that morphological filters feature the property of being invariant with respect to any change of contrast. First, we show that minimization of L/sup 1/ + TV yields a self-dual and contrast invariant filter. Then, we further constrain the minimization process by only optimizing the grey levels of level sets of the image while keeping their boundaries fixed. This new constraint is maintained thanks to the fast level set transform, which yields a complete representation of the image as a tree. We show that this filter can be expressed as a Markov random field on this tree. Finally, we present some results that demonstrate that these new filters can be particularly useful as a pre-processing stage before segmentation.
{"title":"Total variation minimization with L/sup 1/ data fidelity as a contrast invariant filter","authors":"J. Darbon","doi":"10.1109/ISPA.2005.195413","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195413","url":null,"abstract":"This paper sheds new light on minimization of the total variation under the L/sup 1/-norm as data fidelity term (L/sup 1/ +TV) and its link with mathematical morphology. It is well known that morphological filters feature the property of being invariant with respect to any change of contrast. First, we show that minimization of L/sup 1/ + TV yields a self-dual and contrast invariant filter. Then, we further constrain the minimization process by only optimizing the grey levels of level sets of the image while keeping their boundaries fixed. This new constraint is maintained thanks to the fast level set transform, which yields a complete representation of the image as a tree. We show that this filter can be expressed as a Markov random field on this tree. Finally, we present some results that demonstrate that these new filters can be particularly useful as a pre-processing stage before segmentation.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131604143","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195433
G. Vuckovic, B. Dežman, J. Pers, S. Kovacic
In this paper, we present a study on squash player work-rate during the squash matches of two different quality levels. To assess work-rate, the measurement of certain parameters of player motion is needed. The computer vision based software application was used to automatically obtain player motion data from the digitized video recordings of 22 squash matches. The matches were played on two quality levels - international and Slovene national players. We present the results of work-rate comparison between these two groups of players based on game duration and distance covered by the players. We found that the players on the international quality level on average cover significantly larger distances, which is partially caused by longer average game durations.
{"title":"Motion analysis of the international and national rank squash players","authors":"G. Vuckovic, B. Dežman, J. Pers, S. Kovacic","doi":"10.1109/ISPA.2005.195433","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195433","url":null,"abstract":"In this paper, we present a study on squash player work-rate during the squash matches of two different quality levels. To assess work-rate, the measurement of certain parameters of player motion is needed. The computer vision based software application was used to automatically obtain player motion data from the digitized video recordings of 22 squash matches. The matches were played on two quality levels - international and Slovene national players. We present the results of work-rate comparison between these two groups of players based on game duration and distance covered by the players. We found that the players on the international quality level on average cover significantly larger distances, which is partially caused by longer average game durations.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127869679","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 : 2005-10-24DOI: 10.1109/ISPA.2005.195398
P. Eliat, J. Bézy-Wendling, D. Baille-Barrelle, M. Kretowski, D. Olivié
In this paper, we propose to use functional modeling to extract physiological characteristics from dynamic gadolinium-enhanced MRI. The clinical objective is to independently compute the two vascular supplies of the liver, coming from hepatic artery and portal vein. These supplies are progressively modified in hepatocarcinogenesis, and their assessment can be useful for nodule characterization. A first physiological microscopic model of liver vascularization, allows simulating the evolution of the contrast material concentration. After comparison of simulated and real curves, a simplified version of this model is used to extract arterial and portal perfusion parameters, in normal case and in hepatic nodules. These values are in accordance with data obtained by invasive methods.
{"title":"Functional modeling for liver imaging and nodule characterization","authors":"P. Eliat, J. Bézy-Wendling, D. Baille-Barrelle, M. Kretowski, D. Olivié","doi":"10.1109/ISPA.2005.195398","DOIUrl":"https://doi.org/10.1109/ISPA.2005.195398","url":null,"abstract":"In this paper, we propose to use functional modeling to extract physiological characteristics from dynamic gadolinium-enhanced MRI. The clinical objective is to independently compute the two vascular supplies of the liver, coming from hepatic artery and portal vein. These supplies are progressively modified in hepatocarcinogenesis, and their assessment can be useful for nodule characterization. A first physiological microscopic model of liver vascularization, allows simulating the evolution of the contrast material concentration. After comparison of simulated and real curves, a simplified version of this model is used to extract arterial and portal perfusion parameters, in normal case and in hepatic nodules. These values are in accordance with data obtained by invasive methods.","PeriodicalId":238993,"journal":{"name":"ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131682454","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：