原创力文档- 1、本文档共8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
查看更多
Funnel-structured cascade for multi-view face detection with alignment-awareness.pdf
Neurocomputing 221 (2017) 138–145
Contents lists available at ScienceDirect
Neurocomputing
journal homepage: /locate/neucom
crossmarkFunnel-structured cascade for multi-view face detection with alignment-
awareness
Shuzhe Wua, Meina Kana,b, Zhenliang Hea, Shiguang Shana,b,?, Xilin Chena
a Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing 100190, China b CAS Center for Excellence in Brain Science and Intelligence Technology, China
ARTICLE INFO
Communicated by Zhou Xiuzhuang Keywords: Face detection Multi-view Cascade Multilayer perceptron
ABSTRACT
Multi-view face detection in open environment is a challenging task due to diverse variations of face appearances and shapes. Most multi-view face detectors depend on multiple models and organize them in parallel, pyramid or tree structure, which compromise between the accuracy and time-cost. Aiming at a more favorable multi-view face detector, we propose a novel funnel-structured cascade (FuSt) detection framework. In a coarse-to-?ne ?avor, our FuSt consists of, from top to bottom, (1) multiple view-speci?c fast LAB cascade for extremely quick face proposal, (2) multiple coarse MLP cascade for further candidate window veri?cation, and (3) a uni?ed ?ne MLP cascade with shape-indexed features for accurate face detection. Compared with other structures, on the one hand, the proposed one uses multiple computationally e?cient distributed classi?ers to propose a small number of candidate windows but with a high recall of multi-view faces. On the other hand, by using a uni?ed MLP cascade to examine proposals of all views in a centralized style, it provides a favorable solution for multi-view face detection with high accuracy and low time–cost. Besides, the FuSt detector is alignment-aware and performs a coarse facial part prediction which is bene?cial for subsequent face alignment. Extensive experiments on two challenging datasets, FDDB and A
您可能关注的文档
- Evaluation of mechanical performance of NiCo nanocoated aerospace aluminum alloy using quantitative photo-thermo-mechanical radiometry as a non-contact strain gauge.pdf
- Evaluation of pigment location in tinted soft contact lenses.pdf
- Evaluation of rotated upwind schemes for contact discontinuity and strong shock.pdf
- Evaluation of two-view geometry methods with automatic ground-truth generation.pdf
- Evaporating thin film profile near the contact line of a partially wetting water droplet under environmental heating.pdf
- Everyday experimentation in energy transition A practice-theoretical view.pdf
- Evidence of contact activation in patients suffering from ST-elevation myocardial infarction.pdf
- Evolution of the Kaapvaal Craton as viewed from geochemical and SmNd isotopic analyses of intracratonic pelites.pdf
- Examining view angle effects on leaf N estimation in wheat using field reflectance spectroscopy.pdf
- Exceeding 3 ms Minority Carrier Lifetime in n–type Non-contact Crucible Silicon.pdf
文档评论（0）