The rejection of non-meaningful activities is an important issue in human activity recognition (HAR) systems. This rejection is often operated as a hypothesis test based on a model representing all non-meaningful patterns. Such a 'non-meaningful' model is often difficult to obtain in reality. This paper presents a new test, the pairwise likelihood ratio test (PLRT), to reject non-meaningful activities. The model for non-meaningful activities is not required in this test. Moreover, instead of using a fixed likelihood-ratio threshold, the distribution of the likelihood ratios is used as a measurement to improve the rejection accuracy. Two approaches to combine multiple PLRTs into a stronger classifier are also presented
{"title":"Rejection of Non-meaningful Activities","authors":"Liu Xiao-hui, Chua Chin-Seng","doi":"10.1109/FGR.2006.91","DOIUrl":"https://doi.org/10.1109/FGR.2006.91","url":null,"abstract":"The rejection of non-meaningful activities is an important issue in human activity recognition (HAR) systems. This rejection is often operated as a hypothesis test based on a model representing all non-meaningful patterns. Such a 'non-meaningful' model is often difficult to obtain in reality. This paper presents a new test, the pairwise likelihood ratio test (PLRT), to reject non-meaningful activities. The model for non-meaningful activities is not required in this test. Moreover, instead of using a fixed likelihood-ratio threshold, the distribution of the likelihood ratios is used as a measurement to improve the rejection accuracy. Two approaches to combine multiple PLRTs into a stronger classifier are also presented","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"34 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":"116690097","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}
Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures
{"title":"Using a tensor framework for the analysis of facial dynamics","authors":"Lisa Gralewski, N. Campbell, I. Penton-Voak","doi":"10.1109/FGR.2006.108","DOIUrl":"https://doi.org/10.1109/FGR.2006.108","url":null,"abstract":"Research has shown that the dynamics of facial motion are important in the perception of gender, identity, and emotion. In this paper we show that it is possible to use a multilinear tensor framework to extract facial motion signatures and to cluster these signatures by gender or by emotion. Here we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids and mouth) so as to remove structural and shape cues to identity and gender. Such structural gender biases include jaw width and forehead shape and their removal ensures dynamic cues alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor framework, by consistently synthesising new motion signatures","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"53 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":"116711022","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 approach that combines computer vision and decision theory for an automatic video conference system. The setting is a video conference room in which a speaker interacts with surrounding objects, such as a computer, notes and books. Among a set of cameras, the system selects the most appropriate to show to the audience, according to the speaker activity. We assume that the activity of the speaker can be recognized based on hand gestures, and their interaction with the objects in the environment. The proposed approach combines context-based gesture recognition with a decision theoretic model to select the best view. Gesture recognition is based on hidden Markov models, combining motion and contextual information, where the context refers to the relation of the position of the hand with other objects. The posterior probability of each gesture is used in a partially observable Markov decision process (POMDP), to select the best view according to a utility function. The POMDP is implemented as a dynamic Bayesian network with certain lookahead. Preliminary experiments show good results in both, gesture recognition and view selection. We also present the effect of different lookahead periods in the performance of the system
{"title":"A Decision-Theoretic Video Conference System Based on Gesture Recognition","authors":"J.A. Montero, L. Sucar","doi":"10.1109/FGR.2006.7","DOIUrl":"https://doi.org/10.1109/FGR.2006.7","url":null,"abstract":"This paper presents a new approach that combines computer vision and decision theory for an automatic video conference system. The setting is a video conference room in which a speaker interacts with surrounding objects, such as a computer, notes and books. Among a set of cameras, the system selects the most appropriate to show to the audience, according to the speaker activity. We assume that the activity of the speaker can be recognized based on hand gestures, and their interaction with the objects in the environment. The proposed approach combines context-based gesture recognition with a decision theoretic model to select the best view. Gesture recognition is based on hidden Markov models, combining motion and contextual information, where the context refers to the relation of the position of the hand with other objects. The posterior probability of each gesture is used in a partially observable Markov decision process (POMDP), to select the best view according to a utility function. The POMDP is implemented as a dynamic Bayesian network with certain lookahead. Preliminary experiments show good results in both, gesture recognition and view selection. We also present the effect of different lookahead periods in the performance of the system","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"8 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":"117207618","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}
Human face features can be divided in two sets: internal features (composed by eyes, nose and mouth) and external features (located at head, chin, and ears). In general face classification problems, only the internal information is commonly used since this is more difficult to imitate. Nevertheless, nowadays a lot of face verification applications not related to security are developed, and in these cases the contribution of external features for classification purposes should be revised. In this paper, we propose a complete scheme based on a top-down reconstruction algorithm to extract external features of face images. Face verification experiments are performed to test our system and the obtained results show that the information contributed by the external features is specially significant and useful for verification purposes when faces are partially occluded
{"title":"Face Verification using External Features","authors":"Àgata Lapedriza, D. Masip, Jordi Vitrià","doi":"10.1109/FGR.2006.48","DOIUrl":"https://doi.org/10.1109/FGR.2006.48","url":null,"abstract":"Human face features can be divided in two sets: internal features (composed by eyes, nose and mouth) and external features (located at head, chin, and ears). In general face classification problems, only the internal information is commonly used since this is more difficult to imitate. Nevertheless, nowadays a lot of face verification applications not related to security are developed, and in these cases the contribution of external features for classification purposes should be revised. In this paper, we propose a complete scheme based on a top-down reconstruction algorithm to extract external features of face images. Face verification experiments are performed to test our system and the obtained results show that the information contributed by the external features is specially significant and useful for verification purposes when faces are partially occluded","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"2 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":"123783093","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}
ZhenQiu Zhang, G. Potamianos, Ming Liu, Thomas S. Huang
Robust face detection presents a difficult problem in real interaction scenarios, that, in order to achieve, most often requires employing additional sources of information. In this paper, we consider two such sources: temporal information, available in the form of video sequences, and spatial information, available from multiple calibrated cameras with synchronous, overlapping fields of view of the 3D scene of interest. These two sources are exploited jointly, using a novel dynamic programming approach, for a lecture scenario inside appropriately equipped smart rooms, aiming at robust face detection of the lecturer within the available 2D camera views. Experimental results, reported on the CHIL project database, demonstrate that the proposed approach outperforms purely frame-based face detection
{"title":"Robust Multi-View Multi-Camera Face Detection inside Smart Rooms Using Spatio-Temporal Dynamic Programming","authors":"ZhenQiu Zhang, G. Potamianos, Ming Liu, Thomas S. Huang","doi":"10.1109/FGR.2006.98","DOIUrl":"https://doi.org/10.1109/FGR.2006.98","url":null,"abstract":"Robust face detection presents a difficult problem in real interaction scenarios, that, in order to achieve, most often requires employing additional sources of information. In this paper, we consider two such sources: temporal information, available in the form of video sequences, and spatial information, available from multiple calibrated cameras with synchronous, overlapping fields of view of the 3D scene of interest. These two sources are exploited jointly, using a novel dynamic programming approach, for a lecture scenario inside appropriately equipped smart rooms, aiming at robust face detection of the lecturer within the available 2D camera views. Experimental results, reported on the CHIL project database, demonstrate that the proposed approach outperforms purely frame-based face detection","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"62 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":"125336772","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}
As an extension to prior work by the authors in the area of photometric normalisation for face verification, we apply these algorithms in a component-based framework. In particular, we investigate how the requirement for complexity of the normalisation changes when smaller image patches are used. We show that for smaller image patches, a simpler normalisation can out-perform a more complicated method. In addition, we show that a method that applies a simpler normalisation to a number of smaller face image components that are then fused, out-performs a more complicated method applied to the full face image
{"title":"Photometric normalisation for component-based face verification","authors":"J. Short, J. Kittler, K. Messer","doi":"10.1109/FGR.2006.86","DOIUrl":"https://doi.org/10.1109/FGR.2006.86","url":null,"abstract":"As an extension to prior work by the authors in the area of photometric normalisation for face verification, we apply these algorithms in a component-based framework. In particular, we investigate how the requirement for complexity of the normalisation changes when smaller image patches are used. We show that for smaller image patches, a simpler normalisation can out-perform a more complicated method. In addition, we show that a method that applies a simpler normalisation to a number of smaller face image components that are then fused, out-performs a more complicated method applied to the full face image","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"114 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":"122959573","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}
One of the major problem in face authentication systems is to deal with variations in illumination. In a realistic scenario, it is very likely that the lighting conditions of the probe image does not correspond to those of the gallery image, hence there is a need to handle such variations. In this work, we present a new preprocessing algorithm based on local binary patterns (LBP): a texture representation is derived from the input face image before being forwarded to the classifier. The efficiency of the proposed approach is empirically demonstrated using both an appearance-based (LDA) and a feature-based (HMM) face authentication systems on two databases: BANCA and XM2VTS (with its darkened set). Conducted experiments show a significant improvement in terms of verification error rates and compare to results obtained with state-of-the-art preprocessing techniques
{"title":"Local binary patterns as an image preprocessing for face authentication","authors":"G. Heusch, Yann Rodriguez, S. Marcel","doi":"10.1109/FGR.2006.72","DOIUrl":"https://doi.org/10.1109/FGR.2006.72","url":null,"abstract":"One of the major problem in face authentication systems is to deal with variations in illumination. In a realistic scenario, it is very likely that the lighting conditions of the probe image does not correspond to those of the gallery image, hence there is a need to handle such variations. In this work, we present a new preprocessing algorithm based on local binary patterns (LBP): a texture representation is derived from the input face image before being forwarded to the classifier. The efficiency of the proposed approach is empirically demonstrated using both an appearance-based (LDA) and a feature-based (HMM) face authentication systems on two databases: BANCA and XM2VTS (with its darkened set). Conducted experiments show a significant improvement in terms of verification error rates and compare to results obtained with state-of-the-art preprocessing techniques","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"1 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":"116615507","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 global approach to hand gesture vocabulary design is proposed which includes human as well as technical design factors. The human centered desires of multiple users are implicitly represented through indices obtained from ergonomic studies representing the psychophysiological aspects of users. The main technical aspect considered is that of machine recognition of gestures. We review and classify three approaches to this problem: ad hoc, rule based, and analytical. It is believed that this is the first conceptualization of the optimal hand gesture design problem in analytical form. A mathematical dual objective model is developed, which reflects the psychophysiological and technical performance measures upon which a gesture control system is judged. The mathematical program solves a quadratic assignment problem embedded within a heuristic search tree. The quadratic problem, whose solution is a gesture vocabulary GV, (a command-gesture matching) is solved through simulated annealing. A useful feature, included in the formulation, is the priorities given to the matching of complementary pairs of gestures (say thumb up - thumb down) to complementary pairs of commands (say up - down). To validate the procedure an example is solved for the design of a medium size robot command GV
{"title":"Optimal Hand Gesture Vocabulary Design Using Psycho-Physiological and Technical Factors","authors":"H. Stern, J. Wachs, Y. Edan","doi":"10.1109/FGR.2006.84","DOIUrl":"https://doi.org/10.1109/FGR.2006.84","url":null,"abstract":"A global approach to hand gesture vocabulary design is proposed which includes human as well as technical design factors. The human centered desires of multiple users are implicitly represented through indices obtained from ergonomic studies representing the psychophysiological aspects of users. The main technical aspect considered is that of machine recognition of gestures. We review and classify three approaches to this problem: ad hoc, rule based, and analytical. It is believed that this is the first conceptualization of the optimal hand gesture design problem in analytical form. A mathematical dual objective model is developed, which reflects the psychophysiological and technical performance measures upon which a gesture control system is judged. The mathematical program solves a quadratic assignment problem embedded within a heuristic search tree. The quadratic problem, whose solution is a gesture vocabulary GV, (a command-gesture matching) is solved through simulated annealing. A useful feature, included in the formulation, is the priorities given to the matching of complementary pairs of gestures (say thumb up - thumb down) to complementary pairs of commands (say up - down). To validate the procedure an example is solved for the design of a medium size robot command GV","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"72 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":"129011073","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}
Zhihong Zeng, Yun Fu, Glenn I. Roisman, Zhen Wen, Yuxiao Hu, Thomas S. Huang
In this paper, we explore one-class classification application in recognizing emotional and nonemotional facial expressions occurred in a realistic human conversation setting - adult attachment interview (AAI). Although emotional facial expressions are defined in terms of facial action units in the psychological study, non-emotional facial expressions have not distinct description. It is difficult and expensive to model non-emotional facial expressions. Thus, we treat this facial expression recognition as a one-class classification problem which is to describe target objects (i.e. emotional facial expressions) and distinguish them from outliers (i. e. non-emotional ones). We first apply Kernel whitening to map the emotional data in a kernel subspace with unit variances in all directions. Then, we use support vector data description (SVDD) for the classification which is to directly fit a boundary with minimal volume around the target data. We present our preliminary experiments on the AAI data, and compare Kernel whitening SVDD with PCA+SVDD and PCA+Gaussian methods
{"title":"One-class classification for spontaneous facial expression analysis","authors":"Zhihong Zeng, Yun Fu, Glenn I. Roisman, Zhen Wen, Yuxiao Hu, Thomas S. Huang","doi":"10.1109/FGR.2006.83","DOIUrl":"https://doi.org/10.1109/FGR.2006.83","url":null,"abstract":"In this paper, we explore one-class classification application in recognizing emotional and nonemotional facial expressions occurred in a realistic human conversation setting - adult attachment interview (AAI). Although emotional facial expressions are defined in terms of facial action units in the psychological study, non-emotional facial expressions have not distinct description. It is difficult and expensive to model non-emotional facial expressions. Thus, we treat this facial expression recognition as a one-class classification problem which is to describe target objects (i.e. emotional facial expressions) and distinguish them from outliers (i. e. non-emotional ones). We first apply Kernel whitening to map the emotional data in a kernel subspace with unit variances in all directions. Then, we use support vector data description (SVDD) for the classification which is to directly fit a boundary with minimal volume around the target data. We present our preliminary experiments on the AAI data, and compare Kernel whitening SVDD with PCA+SVDD and PCA+Gaussian methods","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"1 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":"130560377","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}
Peter Huisman, R. Munster, S.E. Moro-Ellenberger, R. Veldhuis, A. Bazen
The problem of pose in 2D face recognition is widely acknowledged. Commercial systems are limited to near frontal face images and cannot deal with pose deviations larger than 15 degrees from the frontal view. This is a problem, when using face recognition for surveillance applications in which people can move freely. We suggest a preprocessing step to warp faces from a non frontal pose to a near frontal pose. We use view-based active appearance models to fit to a novel face image under a random pose. The model parameters are adjusted to correct for the pose and used to reconstruct the face under a novel pose. This preprocessing makes face recognition more robust with respect to variations in the pose. An improvement in the identification rate of 60% (from 15% to 75%) is obtained for faces under a pose of 45 degrees
{"title":"Making 2D face recognition more robust using AAMs for pose compensation","authors":"Peter Huisman, R. Munster, S.E. Moro-Ellenberger, R. Veldhuis, A. Bazen","doi":"10.1109/FGR.2006.75","DOIUrl":"https://doi.org/10.1109/FGR.2006.75","url":null,"abstract":"The problem of pose in 2D face recognition is widely acknowledged. Commercial systems are limited to near frontal face images and cannot deal with pose deviations larger than 15 degrees from the frontal view. This is a problem, when using face recognition for surveillance applications in which people can move freely. We suggest a preprocessing step to warp faces from a non frontal pose to a near frontal pose. We use view-based active appearance models to fit to a novel face image under a random pose. The model parameters are adjusted to correct for the pose and used to reconstruct the face under a novel pose. This preprocessing makes face recognition more robust with respect to variations in the pose. An improvement in the identification rate of 60% (from 15% to 75%) is obtained for faces under a pose of 45 degrees","PeriodicalId":109260,"journal":{"name":"7th International Conference on Automatic Face and Gesture Recognition (FGR06)","volume":"29 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":"126843853","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：