Pub Date : 2007-11-12DOI: 10.1109/ICIP.2007.4379196
H. L. Kennedy
Two statistical measures of similarity, for data association and tracking moving objects in sequences of color images, are derived and their performance is compared with normalized cross-correlation. Both methods use an F-distributed test statistic in a hypothesis test, which permits association thresholds to be set to give the desired (theoretical) false-association rate. One of the methods matches the performance of normalized cross-correlation, in the test data used, and is computationally less expensive.
{"title":"Two Statistical Measures of Similarity for Object Association and Tracking in Color Image Sequences","authors":"H. L. Kennedy","doi":"10.1109/ICIP.2007.4379196","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379196","url":null,"abstract":"Two statistical measures of similarity, for data association and tracking moving objects in sequences of color images, are derived and their performance is compared with normalized cross-correlation. Both methods use an F-distributed test statistic in a hypothesis test, which permits association thresholds to be set to give the desired (theoretical) false-association rate. One of the methods matches the performance of normalized cross-correlation, in the test data used, and is computationally less expensive.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127488294","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4378933
Ding Yuan, R. Chung
Calibrating the relative geometry between cameras which would move against one another from time to time is an important problem in multi-camera system. Most of the existing calibration technologies are based on the cross-camera feature correspondences. This paper presents a new solution method. The method demands image data captured under a rigid motion of the camera pair, but unlike the existing motion correspondence-based calibration methods, it does not estimate optical flows nor motion correspondences explicitly. Instead it estimates the inter-camera geometry from the observations that are directly available from the two image streams -the monocular normal flows. Experimental results on real image data are shown to illustrate the feasibility of the solution.
{"title":"Camera-to-Camera Geometry Estimation Requiring no Overlap in their Visual Fields","authors":"Ding Yuan, R. Chung","doi":"10.1109/ICIP.2007.4378933","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4378933","url":null,"abstract":"Calibrating the relative geometry between cameras which would move against one another from time to time is an important problem in multi-camera system. Most of the existing calibration technologies are based on the cross-camera feature correspondences. This paper presents a new solution method. The method demands image data captured under a rigid motion of the camera pair, but unlike the existing motion correspondence-based calibration methods, it does not estimate optical flows nor motion correspondences explicitly. Instead it estimates the inter-camera geometry from the observations that are directly available from the two image streams -the monocular normal flows. Experimental results on real image data are shown to illustrate the feasibility of the solution.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127542946","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379127
Fangfang Lu, Hongdong Li
In this paper, we present an iterative approach to Fisher discriminant analysis called Kullback-Leibler discriminant analysis (KLDA) for both linear and nonlinear feature extraction. We pose the conventional problem of discriminative feature extraction into the setting of function optimization and recover the feature transformation matrix via maximization of the objective function. The proposed objective function is defined by pairwise distances between all pairs of classes and the Kullback-Leibler divergence is adopted to measure the disparity between the distributions of each pair of classes. Our proposed algorithm can be naturally extended to handle nonlinear data by exploiting the kernel trick. Experimental results on the real world databases demonstrate the effectiveness of both the linear and kernel versions of our algorithm.
{"title":"KLDA - An Iterative Approach to Fisher Discriminant Analysis","authors":"Fangfang Lu, Hongdong Li","doi":"10.1109/ICIP.2007.4379127","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379127","url":null,"abstract":"In this paper, we present an iterative approach to Fisher discriminant analysis called Kullback-Leibler discriminant analysis (KLDA) for both linear and nonlinear feature extraction. We pose the conventional problem of discriminative feature extraction into the setting of function optimization and recover the feature transformation matrix via maximization of the objective function. The proposed objective function is defined by pairwise distances between all pairs of classes and the Kullback-Leibler divergence is adopted to measure the disparity between the distributions of each pair of classes. Our proposed algorithm can be naturally extended to handle nonlinear data by exploiting the kernel trick. Experimental results on the real world databases demonstrate the effectiveness of both the linear and kernel versions of our algorithm.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125104368","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379004
N. Noury, F. Sur, M. Berger
This paper presents a probabilistic framework for computing correspondences and fundamental matrix in the structure from motion problem. Inspired by Moisan and Stival [1], we suggest using an a contrario model, which is a good answer to threshold problems in the robust filtering context. Contrary to most existing algorithms where perceptual correspondence setting and geometry evaluation are independent steps, the proposed algorithm is an all-in-one approach. We show that it is robust to repeated patterns which are usually difficult to unambiguously match and thus raise many problems in the fundamental matrix estimation.
{"title":"Fundamental Matrix Estimation Without Prior Match","authors":"N. Noury, F. Sur, M. Berger","doi":"10.1109/ICIP.2007.4379004","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379004","url":null,"abstract":"This paper presents a probabilistic framework for computing correspondences and fundamental matrix in the structure from motion problem. Inspired by Moisan and Stival [1], we suggest using an a contrario model, which is a good answer to threshold problems in the robust filtering context. Contrary to most existing algorithms where perceptual correspondence setting and geometry evaluation are independent steps, the proposed algorithm is an all-in-one approach. We show that it is robust to repeated patterns which are usually difficult to unambiguously match and thus raise many problems in the fundamental matrix estimation.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125971979","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379241
S. Wongthanavasu, V. Tangvoraphonkchai
This paper presents cellular automata algorithms for medical image processing. Mammogram images are comprehensively carried out to determine the hypothesis spots of breast cancer. In this respect, the main cellular automata algorithm and its variation are presented and studied to deal with binary and grayscale images. The results of the proposed algorithms are promising and helpful for physician and doctors in diagnosis of the breast cancer in further steps.
{"title":"Cellular Automata-Based Algorithm and its Application in Medical Image Processing","authors":"S. Wongthanavasu, V. Tangvoraphonkchai","doi":"10.1109/ICIP.2007.4379241","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379241","url":null,"abstract":"This paper presents cellular automata algorithms for medical image processing. Mammogram images are comprehensively carried out to determine the hypothesis spots of breast cancer. In this respect, the main cellular automata algorithm and its variation are presented and studied to deal with binary and grayscale images. The results of the proposed algorithms are promising and helpful for physician and doctors in diagnosis of the breast cancer in further steps.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126174116","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4380014
C. Bouvier, P. Coulon, X. Maldague
Lips segmentation is a very important step in many applications such as automatic speech reading, MPEG-4 compression, special effects, facial analysis and emotion recognition. In this paper, we present a robust method for unsupervised lips segmentation. First the color of the lips area is estimated using expectation maximization and a membership map of the lips is computed from the skin color distribution. The region of interest (ROI) is then found by automatic thresholding on the membership map. Given a mask of the ROI, we initialize a snake that is fitted on the upper and lower contour of the mouth by multi level gradient flow maximization. Finally to find the mouth corners and the final contour of the mouth, we use a parametric model composed of cubic curves and Bezier curves.
{"title":"Unsupervised Lips Segmentation Based on ROI Optimisation and Parametric Model","authors":"C. Bouvier, P. Coulon, X. Maldague","doi":"10.1109/ICIP.2007.4380014","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4380014","url":null,"abstract":"Lips segmentation is a very important step in many applications such as automatic speech reading, MPEG-4 compression, special effects, facial analysis and emotion recognition. In this paper, we present a robust method for unsupervised lips segmentation. First the color of the lips area is estimated using expectation maximization and a membership map of the lips is computed from the skin color distribution. The region of interest (ROI) is then found by automatic thresholding on the membership map. Given a mask of the ROI, we initialize a snake that is fitted on the upper and lower contour of the mouth by multi level gradient flow maximization. Finally to find the mouth corners and the final contour of the mouth, we use a parametric model composed of cubic curves and Bezier curves.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126194592","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379763
P. Aguiar, José M. F. Moura
When the scene background is known and the intensity of moving objects contrasts with the intensity of the background, the objects are easily captured by exploiting occlusion, e.g., background-subtraction. However, when processing general scenes, the background is not known and researchers have mostly attempted to segment moving objects by using motion cues rather than occlusion. Since motion can only be accurately computed at highly textured regions, current motion segmentation methods either fail to segment low textured objects, or require expensive regularization techniques. We present a computationally simple algorithm and test it with segmentation of moving objects in low texture / low contrast videos that are obtained in low-light scenes. The images in the sequence are modeled taking into account the rigidity of the moving object and the occlusion of the background. We formulate the problem as the minimization of a penalized likelihood cost. Relaxation of the weight of the penalty term leads to a simple solution to the nonlinear minimization. We describe experiments that illustrate the good performance of our method.
{"title":"Joint Segmentation of Moving Object and Estimation of Background in Low-Light Video using Relaxation","authors":"P. Aguiar, José M. F. Moura","doi":"10.1109/ICIP.2007.4379763","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379763","url":null,"abstract":"When the scene background is known and the intensity of moving objects contrasts with the intensity of the background, the objects are easily captured by exploiting occlusion, e.g., background-subtraction. However, when processing general scenes, the background is not known and researchers have mostly attempted to segment moving objects by using motion cues rather than occlusion. Since motion can only be accurately computed at highly textured regions, current motion segmentation methods either fail to segment low textured objects, or require expensive regularization techniques. We present a computationally simple algorithm and test it with segmentation of moving objects in low texture / low contrast videos that are obtained in low-light scenes. The images in the sequence are modeled taking into account the rigidity of the moving object and the occlusion of the background. We formulate the problem as the minimization of a penalized likelihood cost. Relaxation of the weight of the penalty term leads to a simple solution to the nonlinear minimization. We describe experiments that illustrate the good performance of our method.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125547693","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379980
C. Manders, F. Farbiz, Steve Mann
The paper proposes a method of compressing floating-point images of arbitrary precision. The concept of floating point images is used frequently in such areas as high dynamic range imaging, where pixel data stored as 8 or 12-bit integers are insufficient. The compression scheme presented in the paper organizes the floating point data in a manner such that already existing compression algorithms such as JPEG or Zlib compression may be used once the data re-organization has taken place. The paper compares the result to a popular (but restrictive) form of image compression, openEXR, and shows significant gains over this format. Furthermore, the compression scheme presented is scalable to deal with floating point images of arbitrary precision.
{"title":"A Compression Method for Arbitrary Precision Floating-Point Images","authors":"C. Manders, F. Farbiz, Steve Mann","doi":"10.1109/ICIP.2007.4379980","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379980","url":null,"abstract":"The paper proposes a method of compressing floating-point images of arbitrary precision. The concept of floating point images is used frequently in such areas as high dynamic range imaging, where pixel data stored as 8 or 12-bit integers are insufficient. The compression scheme presented in the paper organizes the floating point data in a manner such that already existing compression algorithms such as JPEG or Zlib compression may be used once the data re-organization has taken place. The paper compares the result to a popular (but restrictive) form of image compression, openEXR, and shows significant gains over this format. Furthermore, the compression scheme presented is scalable to deal with floating point images of arbitrary precision.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125556346","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379353
Roy M. Frenkel, J. Francos
We address the problem of object registration when the observation differs from the object both geometrically and radio-metrically. The geometric deformations being considered are affine. The radiometric deformations are due to the a-priori lack of knowledge regarding the locations and intensities of the light sources. Hence, to solve the registration problem, a joint solution for the radiometric and the geometric deformations must be offered. A direct approach for solving the joint registration problem as an optimization problem leads to a high-dimensional non-convex search problem. In this paper, we treat the images as vector valued measurements, such that each element of the vector provides the intensity at a specific spectral (color) band. By applying a set of operators, derived in the paper, to the vector valued data the original high-dimensional search problem is replaced by an equivalent problem, expressed in terms of two systems of linear equations. Their solution provides an exact solution to the joint problem.
{"title":"Registration of Geometric Deformations in the Presence of Varying Illumination","authors":"Roy M. Frenkel, J. Francos","doi":"10.1109/ICIP.2007.4379353","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379353","url":null,"abstract":"We address the problem of object registration when the observation differs from the object both geometrically and radio-metrically. The geometric deformations being considered are affine. The radiometric deformations are due to the a-priori lack of knowledge regarding the locations and intensities of the light sources. Hence, to solve the registration problem, a joint solution for the radiometric and the geometric deformations must be offered. A direct approach for solving the joint registration problem as an optimization problem leads to a high-dimensional non-convex search problem. In this paper, we treat the images as vector valued measurements, such that each element of the vector provides the intensity at a specific spectral (color) band. By applying a set of operators, derived in the paper, to the vector valued data the original high-dimensional search problem is replaced by an equivalent problem, expressed in terms of two systems of linear equations. Their solution provides an exact solution to the joint problem.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126608846","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 : 2007-11-12DOI: 10.1109/ICIP.2007.4379212
A. Leone, G. Diraco, C. Distante
This paper presents an inexpensive framework for 3-D seabed mosaic reconstruction, based on an asynchronous stereo vision system when simplifying motion assumptions are used. In order to achieve a metric reconstruction some knowledge about the scene is recovered by a simple and reliable calibration step. The major issue in calibration come from the asynchronism that complicate the proper frames selection. To overcome this problem a stereo frames selection based on epipolar gap evaluation (EGE) is proposed. Stereo disparity maps are evaluated by using both local and global approaches. To deal with brightness constancy model violation, zero-mean normalized cross-correlation is used as similarity measure in local approach, whereas a histogram equalization is necessary in global approach in order to improve min-cut based algorithms. Experimental results validate the proposed framework, allowing to define 3-D mosaics having visual quality similar to those obtained by using specialized hardware.
{"title":"Stereoscopic System for 3-D Seabed Mosaic Reconstruction","authors":"A. Leone, G. Diraco, C. Distante","doi":"10.1109/ICIP.2007.4379212","DOIUrl":"https://doi.org/10.1109/ICIP.2007.4379212","url":null,"abstract":"This paper presents an inexpensive framework for 3-D seabed mosaic reconstruction, based on an asynchronous stereo vision system when simplifying motion assumptions are used. In order to achieve a metric reconstruction some knowledge about the scene is recovered by a simple and reliable calibration step. The major issue in calibration come from the asynchronism that complicate the proper frames selection. To overcome this problem a stereo frames selection based on epipolar gap evaluation (EGE) is proposed. Stereo disparity maps are evaluated by using both local and global approaches. To deal with brightness constancy model violation, zero-mean normalized cross-correlation is used as similarity measure in local approach, whereas a histogram equalization is necessary in global approach in order to improve min-cut based algorithms. Experimental results validate the proposed framework, allowing to define 3-D mosaics having visual quality similar to those obtained by using specialized hardware.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116103411","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：