发布求助
文献互助 智能选刊 最新文献

2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)最新文献

筛选
英文 中文
Illumination normalization for robust face recognition against varying lighting conditions 光照归一化在不同光照条件下的鲁棒人脸识别
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240838
S. Shan, Wen Gao, B. Cao, Debin Zhao
{"title":"Illumination normalization for robust face recognition against varying lighting conditions","authors":"S. Shan, Wen Gao, B. Cao, Debin Zhao","doi":"10.1109/AMFG.2003.1240838","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240838","url":null,"abstract":"Evaluations of the state-of-the-art of both academic face recognition algorithms and commercial systems have shown that recognition performance of most current technologies degrades due to the variations of illumination. We investigate several illumination normalization methods and propose some novel solutions. The main contribution includes: (1) A gamma intensity correction (GIC) method is proposed to normalize the overall image intensity at the given illumination level; (2) A region-based strategy combining GIC and the histogram equalization (HE) is proposed to further eliminate the side-lighting effect; (3) A quotient illumination relighting (QIR) method is presented to synthesize images under a predefined normal lighting condition from the provided face images captured under nonnormal lighting condition. These methods are evaluated and compared on the Yale illumination face database B and Harvard illumination face database. Considerable improvements are observed. Some conclusions are given at last.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130505709","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}
引用次数: 408
Human recognition of familiar and unfamiliar people in naturalistic video 自然主义视频中人类对熟悉和不熟悉的人的识别
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240821
D. Roark, A. O’Toole, H. Abdi
{"title":"Human recognition of familiar and unfamiliar people in naturalistic video","authors":"D. Roark, A. O’Toole, H. Abdi","doi":"10.1109/AMFG.2003.1240821","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240821","url":null,"abstract":"Understanding the human performance factors that mediate successful person identification can be helpful in the development of automatic face recognition algorithms. Face familiarity and facial motion are two factors that seem especially useful when subjects make recognition decisions from challenging viewing formats. We tested the effects of these two factors on person recognition from naturalistic, surveillance-like video. Subjects learned faces from either static photographs or facial speech videos and were asked to recognize people from whole body gait videos. We found that the more experience participants had with a face during learning (i.e., 1-view, 2-view, and 4-view conditions), the better their recognition performance for people in the whole body video gait clips. Thus, familiarizing subjects with high-resolution images or videos of faces was sufficient to improve recognition from low-resolution, whole-body images. Moreover, participants who learned faces from dynamic video clips were more accurate than participants who learned the faces from static images, but only when they were familiar with the faces. Facial motion and face familiarity may therefore play a role in understanding recognition when there are photometric inconsistencies between learning and test stimuli.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131759932","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}
引用次数: 28
Boosted audio-visual HMM for speech reading 增强语音阅读的视听HMM
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240826
Pei Yin, Irfan Essa, James M. Rehg
{"title":"Boosted audio-visual HMM for speech reading","authors":"Pei Yin, Irfan Essa, James M. Rehg","doi":"10.1109/AMFG.2003.1240826","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240826","url":null,"abstract":"We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likelihoods of (a) HMM used to model phonemes from the acoustic signal, and (b) HMM used to model visual features motions from video. One significant addition is the dynamic analysis with features selected by AdaBoost, on the basis of their discriminant ability. This form of integration, leading to boosted HMM, permits AdaBoost to find the best features first, and then uses HMM to exploit dynamic information inherent in the signal.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128584928","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}
引用次数: 5
Real-time view-based face alignment using active wavelet networks 利用有源小波网络进行实时基于视图的人脸对齐
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240846
Changbo Hu, R. Feris, M. Turk
{"title":"Real-time view-based face alignment using active wavelet networks","authors":"Changbo Hu, R. Feris, M. Turk","doi":"10.1109/AMFG.2003.1240846","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240846","url":null,"abstract":"The active wavelet network (AWN) [C. Hu et al., (2003)] approach was recently proposed for automatic face alignment, showing advantages over active appearance models (AAM), such as more robustness against partial occlusions and illumination changes. We (1) extend the AWN method to a view-based approach, (2) verify the robustness of our algorithm with respect to unseen views in a large dataset and (3) show that using only nine wavelets, our method yields similar performance to state-of-the-art face alignment systems, with a significant enhancement in terms of speed. After optimization, our system requires only 3 ms per iteration on a 1.6 GHz Pentium IV. We show applications in face alignment for recognition and real-time facial feature tracking under large pose variations.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131800536","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}
引用次数: 43
Illumination modeling and normalization for face recognition 人脸识别的照明建模和归一化
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240831
Haitao Wang, S. Li, Yangsheng Wang, Weiwei Zhang
{"title":"Illumination modeling and normalization for face recognition","authors":"Haitao Wang, S. Li, Yangsheng Wang, Weiwei Zhang","doi":"10.1109/AMFG.2003.1240831","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240831","url":null,"abstract":"We present a general framework for face modeling under varying lighting conditions. First, we show that a face lighting subspace can be constructed based on three or more training face images illuminated by noncoplanar lights. The lighting of any face image can be represented as a point in this subspace. Second, we show that the extreme rays, i.e. the boundary of an illumination cone, cover the entire light sphere. Therefore, a relatively sparsely sampled face images can be used to build a face model instead of calculating each extremely illuminated face image. Third, we present a face normalization algorithm, illumination alignment, i.e. changing the lighting of one face image to that of another face image. Experiments are presented.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129398051","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}
引用次数: 40
Avoiding replay-attacks in a face recognition system using head-pose estimation 使用头部姿态估计的人脸识别系统避免重放攻击
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240849
Robert Frischholz, Alexander Werner
{"title":"Avoiding replay-attacks in a face recognition system using head-pose estimation","authors":"Robert Frischholz, Alexander Werner","doi":"10.1109/AMFG.2003.1240849","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240849","url":null,"abstract":"The subject is a challenge response mechanism used as an optional add-on to the face recognition part of the multi modal biometric authentication system \"BioID\". This mechanism greatly enhances security in regard to replay attacks. The user is required to look into a certain direction, which is randomly chosen by the system. By estimating the head pose, the system verifies the user's response to the direction challenge. The pose estimation is based on detection and subsequent tracking of suitable facial features. Experimental evaluations have shown the effectiveness of the approach against replay attacks.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132863462","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}
引用次数: 77
Advances in component based face detection 基于分量的人脸检测研究进展
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240837
S. Bileschi, B. Heisele
{"title":"Advances in component based face detection","authors":"S. Bileschi, B. Heisele","doi":"10.1109/AMFG.2003.1240837","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240837","url":null,"abstract":"We describe the design of a component based face detector for gray scale images. We show that including pans of the face into the negative training sets of the component classifiers leads to improved system performance. We also introduce a method of using pairwise position statistics between component locations to more accurately locate the parts of a face. Finally, we illustrate an application of this technology in the creation of an accurate eye detection system.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"94 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133017930","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}
引用次数: 47
Automatic face classifications by self-organization for face recognition 基于自组织的人脸自动分类
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240839
Y. Sato, Ikushi Yoda, K. Sakaue
{"title":"Automatic face classifications by self-organization for face recognition","authors":"Y. Sato, Ikushi Yoda, K. Sakaue","doi":"10.1109/AMFG.2003.1240839","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240839","url":null,"abstract":"We propose a method of face recognition that can consistently identify every face angle, assuming it is used in open spaces such as a normal room. We obtain the learning images not from an ideal world but from the real world, where users can move around freely with no constraints. We then automatically classify the face images that vary according to the user's position and posture by self-organization (unsupervised learning), and create a discrimination circuit using only the best face images for the recognition task. We show that the recognition rate for images with various facial angles in the real world can be improved by automatic classification through self-organization.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114126517","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}
引用次数: 2
Probabilistic tracking and recognition of nonrigid hand motion 非刚性手部运动的概率跟踪与识别
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240825
Huang Fei, I. Reid
{"title":"Probabilistic tracking and recognition of nonrigid hand motion","authors":"Huang Fei, I. Reid","doi":"10.1109/AMFG.2003.1240825","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240825","url":null,"abstract":"Successful tracking of articulated hand motion is the first step in many computer vision applications such as gesture recognition. However the nonrigidity of the hand, complex background scenes, and occlusion make tracking a challenging task. We divide and conquer tracking by decomposing complex motion into nonrigid motion and rigid motion. A learning-based algorithm for analyzing nonrigid motion is presented. In this method, appearance-based models are learned from image data, and underlying motion patterns are explored using a generative model. Nonlinear dynamics of the articulation such as fast appearance deformation can thus be analyzed without resorting to a complex kinematic model. We approximate the rigid motion as planar motion, which can be approached by a filtering method. We unify our treatments of nonrigid motion and rigid motion into a single, robust Bayesian framework and demonstrate the efficacy of this method by performing successful tracking in the presence of significant occlusion clutter.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114332439","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}
引用次数: 17
Pose estimation using 3D view-based eigenspaces 基于三维视图特征空间的姿态估计
2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443) Pub Date : 2003-10-17 DOI: 10.1109/AMFG.2003.1240823
Louis-Philippe Morency, P. Sundberg, Trevor Darrell
{"title":"Pose estimation using 3D view-based eigenspaces","authors":"Louis-Philippe Morency, P. Sundberg, Trevor Darrell","doi":"10.1109/AMFG.2003.1240823","DOIUrl":"https://doi.org/10.1109/AMFG.2003.1240823","url":null,"abstract":"We present a method for estimating the absolute pose of a rigid object based on intensity and depth view-based eigenspaces, built across multiple views of example objects of the same class. Given an initial frame of an object with unknown pose, we reconstruct a prior model for all views represented in the eigenspaces. For each new frame, we compute the pose-changes between every view of the reconstructed prior model and the new frame. The resulting pose-changes are then combined and used in a Kalman filter update. This approach for pose estimation is user-independent and the prior model can be initialized automatically from any viewpoint of the view-based eigenspaces. To track more robustly over time, we present an extension of this pose estimation technique where we integrate our prior model approach with an adaptive differential tracker. We demonstrate the accuracy of our approach on face pose tracking using stereo cameras.","PeriodicalId":388409,"journal":{"name":"2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123291661","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}
引用次数: 83
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书