We study the effect of development set size on system performance, as measured by verification error. The study was performed using the FERET and FRGC2 databases to construct development training sets of varying size, while XM2VTS was used to test the system. Surprisingly, the achievable performance levels off relatively quickly. Increasing the size of the development set does not bring any benefit. On the contrary it may result in performance degradation. This finding appears to be development set independent. However, the choice of the development set size is protocol dependent
{"title":"Database size effects on performance on a smart card face verification system","authors":"T. Bourlai, J. Kittler, K. Messer","doi":"10.1109/FGR.2006.36","DOIUrl":"https://doi.org/10.1109/FGR.2006.36","url":null,"abstract":"We study the effect of development set size on system performance, as measured by verification error. The study was performed using the FERET and FRGC2 databases to construct development training sets of varying size, while XM2VTS was used to test the system. Surprisingly, the achievable performance levels off relatively quickly. Increasing the size of the development set does not bring any benefit. On the contrary it may result in performance degradation. This finding appears to be development set independent. However, the choice of the development set size is protocol dependent","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133690119","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}
This paper details MORPH a longitudinal face database developed for researchers investigating all facets of adult age-progression, e.g. face modeling, photo-realistic animation, face recognition, etc. This database contributes to several active research areas, most notably face recognition, by providing: the largest set of publicly available longitudinal images; longitudinal spans from a few months to over twenty years; and, the inclusion of key physical parameters that affect aging appearance. The direct contribution of this data corpus for face recognition is highlighted in the evaluation of a standard face recognition algorithm, which illustrates the impact that age-progression, has on recognition rates. Assessment of the efficacy of this algorithm is evaluated against the variables of gender and racial origin. This work further concludes that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work
{"title":"MORPH: a longitudinal image database of normal adult age-progression","authors":"K. Ricanek, Tamirat Tesafaye","doi":"10.1109/FGR.2006.78","DOIUrl":"https://doi.org/10.1109/FGR.2006.78","url":null,"abstract":"This paper details MORPH a longitudinal face database developed for researchers investigating all facets of adult age-progression, e.g. face modeling, photo-realistic animation, face recognition, etc. This database contributes to several active research areas, most notably face recognition, by providing: the largest set of publicly available longitudinal images; longitudinal spans from a few months to over twenty years; and, the inclusion of key physical parameters that affect aging appearance. The direct contribution of this data corpus for face recognition is highlighted in the evaluation of a standard face recognition algorithm, which illustrates the impact that age-progression, has on recognition rates. Assessment of the efficacy of this algorithm is evaluated against the variables of gender and racial origin. This work further concludes that the problem of age-progression on face recognition (FR) is not unique to the algorithm used in this work","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133590557","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}
Gabor feature has been widely recognized as one of the best representations for face recognition. However, traditionally, it has to be reduced in dimension due to curse of dimensionality. In this paper, an ensemble based Gabor Fisher classifier (EGFC) method is proposed, which is an ensemble classifier combining multiple Fisher discriminant analysis (FDA)-based component classifiers learnt using different segments of the entire Gabor feature. Since every dimension of the entire Gabor feature is exploited by one component FDA classifier, we argue that EGFC makes better use of the discriminability implied in all the Gabor features by avoiding the dimension reduction procedure. In addition, by carefully controlling the dimension of each feature segment, small sample size (3S) problem commonly confronting FDA is artfully avoided. Experimental results on FERET show that the proposed EGFC significantly outperforms the known best results so far. Furthermore, to speed up, hierarchical EGFC (HEGFC) is proposed based on pyramid-based Gabor representation. Our experiments show that, by using the hierarchical method, the time cost of the HEGFC can be dramatically reduced without much accuracy lost
{"title":"Hierarchical ensemble of Gabor Fisher classifier for face recognition","authors":"Yu Su, S. Shan, Xilin Chen, Wen Gao","doi":"10.1109/FGR.2006.64","DOIUrl":"https://doi.org/10.1109/FGR.2006.64","url":null,"abstract":"Gabor feature has been widely recognized as one of the best representations for face recognition. However, traditionally, it has to be reduced in dimension due to curse of dimensionality. In this paper, an ensemble based Gabor Fisher classifier (EGFC) method is proposed, which is an ensemble classifier combining multiple Fisher discriminant analysis (FDA)-based component classifiers learnt using different segments of the entire Gabor feature. Since every dimension of the entire Gabor feature is exploited by one component FDA classifier, we argue that EGFC makes better use of the discriminability implied in all the Gabor features by avoiding the dimension reduction procedure. In addition, by carefully controlling the dimension of each feature segment, small sample size (3S) problem commonly confronting FDA is artfully avoided. Experimental results on FERET show that the proposed EGFC significantly outperforms the known best results so far. Furthermore, to speed up, hierarchical EGFC (HEGFC) is proposed based on pyramid-based Gabor representation. Our experiments show that, by using the hierarchical method, the time cost of the HEGFC can be dramatically reduced without much accuracy lost","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114446764","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}
In this paper, we present a clustering-based tracking algorithm for tracking people (e.g. hand, head, eyeball, body). A human body often appears as a concave object or an object with apertures. In this case, many background areas are mixed into the tracking target which are difficult to be removed by modifying the shape of the search area during tracking. This algorithm realizes the robust tracking for such objects by classifying the pixels in the search area into "target" and "non-target" with K-means clustering algorithm that uses both the "positive" and "negative" samples. The contributions of this research are: 1) Using a 5-D feature vector to describe both the geometric feature "(x,y)" and color feature "(Y,U,V)" of an object (or a pixel) uniformly. This description ensures our method to follow both the position and color changes simultaneously during tracking; 2) Using a variable ellipse model: (a) to describe the shape of a non-rigid object (e.g. hand) approximately, (b) to restrict the search area, and (c) to model the surrounding non-target background. This guarantees the stable tracking of objects with various geometric transformations. Through extensive experiments in various environments and conditions, the effectiveness and the efficiency of the proposed algorithm is confirmed
{"title":"A general framework for tracking people","authors":"C. Hua, Haiyuan Wu, Qian Chen, T. Wada","doi":"10.1109/FGR.2006.9","DOIUrl":"https://doi.org/10.1109/FGR.2006.9","url":null,"abstract":"In this paper, we present a clustering-based tracking algorithm for tracking people (e.g. hand, head, eyeball, body). A human body often appears as a concave object or an object with apertures. In this case, many background areas are mixed into the tracking target which are difficult to be removed by modifying the shape of the search area during tracking. This algorithm realizes the robust tracking for such objects by classifying the pixels in the search area into \"target\" and \"non-target\" with K-means clustering algorithm that uses both the \"positive\" and \"negative\" samples. The contributions of this research are: 1) Using a 5-D feature vector to describe both the geometric feature \"(x,y)\" and color feature \"(Y,U,V)\" of an object (or a pixel) uniformly. This description ensures our method to follow both the position and color changes simultaneously during tracking; 2) Using a variable ellipse model: (a) to describe the shape of a non-rigid object (e.g. hand) approximately, (b) to restrict the search area, and (c) to model the surrounding non-target background. This guarantees the stable tracking of objects with various geometric transformations. Through extensive experiments in various environments and conditions, the effectiveness and the efficiency of the proposed algorithm is confirmed","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"72 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133587858","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}
We examined the effectiveness of using Haar features and the Adaboost boosting algorithm for FACS action unit (AU) recognition. We evaluated both recognition accuracy and processing time of this new approach compared to the state-of-the-art method of classifying Gabor responses with support vector machines. Empirical results on the Cohn-Kanade facial expression database showed that the Haar+Adaboost method yields AU recognition rates comparable to those of the Gabor+SVM method but operates at least two orders of magnitude more quickly
{"title":"Haar features for FACS AU recognition","authors":"J. Whitehill, C. Omlin","doi":"10.1109/FGR.2006.61","DOIUrl":"https://doi.org/10.1109/FGR.2006.61","url":null,"abstract":"We examined the effectiveness of using Haar features and the Adaboost boosting algorithm for FACS action unit (AU) recognition. We evaluated both recognition accuracy and processing time of this new approach compared to the state-of-the-art method of classifying Gabor responses with support vector machines. Empirical results on the Cohn-Kanade facial expression database showed that the Haar+Adaboost method yields AU recognition rates comparable to those of the Gabor+SVM method but operates at least two orders of magnitude more quickly","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133645659","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}
This paper presents a new method for automatic gait recognition based on analyzing the multiple projections to silhouette using principal components analysis (PCA). Binarized silhouette of a motion object is represented by 1-D signals which are the basic image features called the distance vectors. The distance vectors are differences between the bounding box and silhouette, and extracted using four projections to silhouette. Based on normalized correlation on the distance vectors, gait cycle estimation is first performed to extract the gait cycle. Second, an eigenspace transformation based on PCA is applied to time-varying distance vectors and the statistical distance based supervised pattern classification is then performed in the lower-dimensional eigenspace for human identification. A fusion strategy developed is finally executed to produce final decision. Experimental results on four databases demonstrate that the right person in top two matches 100% of the times for the cases where training and testing sets corresponds to the same walking styles, and in top three-four matches 100% of the times for training and testing sets corresponds to the different walking styles
{"title":"Gait Recognition Using Multiple Projections","authors":"M. Ekinci","doi":"10.1109/FGR.2006.57","DOIUrl":"https://doi.org/10.1109/FGR.2006.57","url":null,"abstract":"This paper presents a new method for automatic gait recognition based on analyzing the multiple projections to silhouette using principal components analysis (PCA). Binarized silhouette of a motion object is represented by 1-D signals which are the basic image features called the distance vectors. The distance vectors are differences between the bounding box and silhouette, and extracted using four projections to silhouette. Based on normalized correlation on the distance vectors, gait cycle estimation is first performed to extract the gait cycle. Second, an eigenspace transformation based on PCA is applied to time-varying distance vectors and the statistical distance based supervised pattern classification is then performed in the lower-dimensional eigenspace for human identification. A fusion strategy developed is finally executed to produce final decision. Experimental results on four databases demonstrate that the right person in top two matches 100% of the times for the cases where training and testing sets corresponds to the same walking styles, and in top three-four matches 100% of the times for training and testing sets corresponds to the different walking styles","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122394655","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}
A set of techniques is presented for extracting essential shape information from image sequences. Presented methods are (i) human detection, (ii) human body parts detection, and (iii) hand shape analysis, all based on depth image streams. In particular, representative types of hand shapes used in Japanese sign language (JSL) are recognized in a non-intrusive manner with a high recognition rate. An experimental JSL recognition system is built that can recognize over 100 words by using an active sensing hardware to capture a stream of depth images at a video rate. Experimental results are shown to validate our approach and characteristics of our approach are discussed
{"title":"Sign recognition using depth image streams","authors":"K. Fujimura, Xia Liu","doi":"10.1109/FGR.2006.101","DOIUrl":"https://doi.org/10.1109/FGR.2006.101","url":null,"abstract":"A set of techniques is presented for extracting essential shape information from image sequences. Presented methods are (i) human detection, (ii) human body parts detection, and (iii) hand shape analysis, all based on depth image streams. In particular, representative types of hand shapes used in Japanese sign language (JSL) are recognized in a non-intrusive manner with a high recognition rate. An experimental JSL recognition system is built that can recognize over 100 words by using an active sensing hardware to capture a stream of depth images at a video rate. Experimental results are shown to validate our approach and characteristics of our approach are discussed","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124919307","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}
This paper presents the application of a kernel particle filter for 3D body tracking in a video stream acquired from a single uncalibrated camera. Using intensity-based and color-based cues as well as an articulated 3D body model with shape represented by cylinders, a real-time body tracking in monocular cluttered image sequences has been realized. The algorithm runs at 7.5 Hz on a laptop computer and tracks the upper body of a human with two arms. First, experimental results show that the proposed approach has good tracking as well as recovering capabilities despite using a small number of particles. The approach is intended for use on a mobile robot to improve human robot interaction
{"title":"Kernel particle filter for real-time 3D body tracking in monocular color images","authors":"Joachim Schmidt, J. Fritsch, B. Kwolek","doi":"10.1109/FGR.2006.69","DOIUrl":"https://doi.org/10.1109/FGR.2006.69","url":null,"abstract":"This paper presents the application of a kernel particle filter for 3D body tracking in a video stream acquired from a single uncalibrated camera. Using intensity-based and color-based cues as well as an articulated 3D body model with shape represented by cylinders, a real-time body tracking in monocular cluttered image sequences has been realized. The algorithm runs at 7.5 Hz on a laptop computer and tracks the upper body of a human with two arms. First, experimental results show that the proposed approach has good tracking as well as recovering capabilities despite using a small number of particles. The approach is intended for use on a mobile robot to improve human robot interaction","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120962325","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}
Efficient 3D face reconstruction is very important for face animation and recognition. The slow speed of the 3D morphable model is due to the texture mapping. To improve the speed, we only use the shape matching to recover the 3D shape and use texture mapping to get the texture. However, only with the shape information, one image is not enough for accurate 3D face reconstruction. So, we propose to use multiple images with the morphable shape model. First, with the feature points given on the multiple images, the 3D coordinates of the feature points are estimate by the pose estimation. Then, frontal and profile 2D morphable shape models are built to estimate the 3D morphable shape model. These two steps works iteratively to improve the result. At last, the texture is extracted from multiple images with the pose estimation from the estimated 3D face. The effectiveness of our method is demonstrated by the experimental results
{"title":"Morphable face reconstruction with multiple images","authors":"Ming Zhao, Tat-Seng Chua, T. Sim","doi":"10.1109/FGR.2006.79","DOIUrl":"https://doi.org/10.1109/FGR.2006.79","url":null,"abstract":"Efficient 3D face reconstruction is very important for face animation and recognition. The slow speed of the 3D morphable model is due to the texture mapping. To improve the speed, we only use the shape matching to recover the 3D shape and use texture mapping to get the texture. However, only with the shape information, one image is not enough for accurate 3D face reconstruction. So, we propose to use multiple images with the morphable shape model. First, with the feature points given on the multiple images, the 3D coordinates of the feature points are estimate by the pose estimation. Then, frontal and profile 2D morphable shape models are built to estimate the 3D morphable shape model. These two steps works iteratively to improve the result. At last, the texture is extracted from multiple images with the pose estimation from the estimated 3D face. The effectiveness of our method is demonstrated by the experimental results","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123247759","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}
Motivated by a recently proposed biologically-inspired face recognition approach, psychophysical experiments have been carried out. We measured recognition performance of polar frequency filtered face images using an 8-alternatives forced-choice method. Test stimuli were generated by converting the images from the spatial to the polar frequency domain using the Fourier-Bessel transformation (FBT), filtering of the resulting coefficients with band-pass filters, and finally taking the inverse FBT of the filtered coefficients. We also evaluated an automatic FBT-based face recognition model. Contrast sensitivity functions of the human observers peaked in the 8-11.3 radial and angular frequency range, with higher peak sensitivity in the former case. The automatic face recognition algorithm presented similar behavior. These results suggest that polar frequency components could be used by the human face processing system and that human performance can be constrained by the polar frequency information content
{"title":"Human and machine recognition of Fourier-Bessel filtered face images","authors":"Y. Zana, R. M. C. Junior, J. Mena-Chalco","doi":"10.1109/FGR.2006.66","DOIUrl":"https://doi.org/10.1109/FGR.2006.66","url":null,"abstract":"Motivated by a recently proposed biologically-inspired face recognition approach, psychophysical experiments have been carried out. We measured recognition performance of polar frequency filtered face images using an 8-alternatives forced-choice method. Test stimuli were generated by converting the images from the spatial to the polar frequency domain using the Fourier-Bessel transformation (FBT), filtering of the resulting coefficients with band-pass filters, and finally taking the inverse FBT of the filtered coefficients. We also evaluated an automatic FBT-based face recognition model. Contrast sensitivity functions of the human observers peaked in the 8-11.3 radial and angular frequency range, with higher peak sensitivity in the former case. The automatic face recognition algorithm presented similar behavior. These results suggest that polar frequency components could be used by the human face processing system and that human performance can be constrained by the polar frequency information content","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123343070","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：