A Fast and Accurate Unconstrained Face Detector

doi:10.1109/TPAMI.2015.2448075

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 生物识别与安全技术

	A Fast and Accurate Unconstrained Face Detector
	Liao, Shengcai1,2 ; Jain, Anil K.3; Li, Stan Z.1,2
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2016-02-01
卷号	38 期号:2 页码:211-223
文章类型	Article
摘要	We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is able to reconstruct the original image. Second, we propose a deep quadratic tree to learn the optimal subset of NPD features and their combinations, so that complex face manifolds can be partitioned by the learned rules. This way, only a single soft-cascade classifier is needed to handle unconstrained face detection. Furthermore, we show that the NPD features can be efficiently obtained from a look up table, and the detection template can be easily scaled, making the proposed face detector very fast. Experimental results on three public face datasets (FDDB, GENKI, and CMU-MIT) show that the proposed method achieves state-of-the-art performance in detecting unconstrained faces with arbitrary pose variations and occlusions in cluttered scenes.
关键词	Unconstrained Face Detection Normalized Pixel Difference Deep Quadratic Tree Adaboost Cascade Classifier
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TPAMI.2015.2448075
关键词[WOS]	RAPID OBJECT DETECTION ; HAAR-LIKE FEATURES ; CASCADE ; RECOGNITION ; SURF
收录类别	SCI
语种	英语
项目资助者	NSFC(61203267) ; National Science and Technology Support Program(2013BAK02B01) ; CAS Project(KGZD-EW-102-2)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000369989600002
引用统计	被引频次：85[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11343
专题	多模态人工智能系统全国重点实验室_生物识别与安全技术
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Ctr Biometr & Secur Res, Inst Automat, Beijing 100190, Peoples R China 3.Michigan State Univ, Dept Comp Sci & Engn, E Lansing, MI 48824 USA
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Liao, Shengcai,Jain, Anil K.,Li, Stan Z.. A Fast and Accurate Unconstrained Face Detector[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2016,38(2):211-223.
APA	Liao, Shengcai,Jain, Anil K.,&Li, Stan Z..(2016).A Fast and Accurate Unconstrained Face Detector.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,38(2),211-223.
MLA	Liao, Shengcai,et al."A Fast and Accurate Unconstrained Face Detector".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 38.2(2016):211-223.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Liao-PAMI15-NPD.pdf（19087KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载