Cross-pose face recognition based on multiple virtual views and alignment error.pdfVIP

下载本文档

19
0
约4.01万字
约 7页
2017-03-16 发布于天津
举报
版权申诉

Cross-pose face recognition based on multiple virtual views and alignment error.pdf

1、本文档共7页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Cross-pose face recognition based on multiple virtual views and alignment error.pdf

Pattern Recognition Letters 65 (2015) 170–176 Contents lists available at ScienceDirect Pattern Recognition Letters journal homepage: /locate/patrec Cross-pose face recognition based on multiple virtual views and alignment error ? Yongbin Gao a, Hyo Jong Lee a,b,? a Division of Computer Science and Engineering, Chonbuk National University, 567 Baekje-Daero, Deokjin-Gu, Jeonju 561756, Republic of Korea b Center for Advanced Image and Information Technology, Chonbuk National University, 567 Baekje-Daero, Deokjin-Gu, Jeonju 561756, Republic of Korea article info Article history: Received 12 November 2014 Available online 11 August 2015 Keywords: Face recognition Virtual views Alignment error abstract Although studied for decades, effective face recognition remains di?cult to accomplish on account of occlusions and pose and illumination variations. Pose variance is a particular challenge in face recognition. Effective local descriptors have been proposed for frontal face recognition. When these descriptors are directly applied to cross-pose face recognition, the performance signi?cantly decreases. To improve the descriptor performance for cross-pose face recognition, we propose a face recognition algorithm based on multiple virtual views and alignment error. First, warps between poses are learned using the Lucas–Kanade algorithm. Based on these warps, multiple virtual pro?le views are generated from a single frontal face, which enables non-frontal faces to be matched using the scale-invariant feature transform (SIFT) algorithm. Furthermore, warps indicate the correspondence between patches of two faces. A two-phase alignment error is proposed to obtain accurate warps, which contain pose alignment and individual alignment. Correlations between patches are considered to calculate the alignment error of two faces. Finally, a hybrid similarity between two faces is calculated; it combines the number of matched keypoints from SIFT and the alignment error. Experimental results