人脸检测研究2015最新进展
http://www.cvrobot.net/latest-progress-in-face-detection-2015/人脸检测研究2015最新进展搜集整理了2004~2015性能最好的人脸检测的部分资料,欢迎交流和补充相关资料。1:人脸检测性能1.1 人脸检测测评 目前有两个比较大的人脸测评网站: 1:Face Detection Data Set and Benchmark(FDDB) 网址:www.cs.umass.edu/fddb/results.html]http://vis-www.cs.umass.edu/fddb/results.html FDDB是由马萨诸塞大学计算机系维护的一套公开数据库,为来自全世界的研究者提供一个标准的人脸检测评测平台,其中涵盖在自然环境下的各种姿态的人脸;该校还维护了LFW等知名人脸数据库供研究者做人脸识别的研究。作为全世界最具权威的人脸检测评测平台之一,FDDB使用Faces in the Wild数据库中的包含5171张人脸的2845张图片作为测试集,而其公布的评测集也代表了人脸检测的世界最高水平。 FDDB更新更及时一些,所以本文的资料还是主要参考的FDDB。 2:Fine-grained evaluation of face detection in the wild 网址:http://www.cbsr.ia.ac.cn/faceEvaluation/results.html 该测试网站是由李子青老师的研究组创立和维护的,其性能评估更细致,分析不同分辨率、角度、性别、年龄等条件下的算法准确率。该测试集更新没有FDDB及时。1.2 Suevey 1)2010年微软zhang cha和张正友撰写的人脸检测的综述报告 A_survey_of_recent_advances_in_face_detection 2)Stefanos Zafeiriou, Cha Zhang和张正友撰写了最新的人脸检测的综述paper,将出版在2016年的《Computer Vision and Image Understanding》 A Survey on Face Detection in the wild past, present and future 最新性能总结如下:http://www.cvrobot.net/wp-content/uploads/2015/06/A-Survey-on-Face-Detection-in-the-wild-past-present-and-future-1024x359.png 1)在过去的10年人脸检测的性能已经有了激动人心的提升。
2)这些引人注目的性能提升,主要还是得益于将Viala-Jones的boosting和鲁棒性的特征相组合。
3)始终有15~20%的性能Gap,即使允许一个相对较大的FP(大约1000),始终有15~10%的人脸无法被检测到。需要特别指出的是这些Gap主要是由于是失焦的人脸(比如模糊的人脸)。
4)在这个Benchmark中,最好的基于boosting技术和最好的基于DPM的技术是比较接近的。当然最好的技术还是boosting和DPM组合在一起的性能。(这个就是指的 Joint Cascade Face Detection and Alignment)1.4 有关人脸检测指标 如果对于人脸检测指标不是很熟悉,可以参考http://www.cvrobot.net/recall-precision-false-positive-false-negative/http://www.cvrobot.net/wp-content/uploads/2015/06/recall-precision-false-positive-false-negative-1.png 2. 2014的进展 1:Joint Cascade Face Detection and Alignment. ECCV 2014. D. Chen, S. Ren, Y. Wei, X. Cao, J. Sun.
Paper: Joint Cascade Face Detection and Alignment 中文介绍:联合人脸检测、校准算法介绍 2:The fastest deformable part model for object detection J. Yan, Z. Lei, L. Wen, S. Z. Li, paper: The Fastest Deformable Part Model for Object Detection 3:Face detection without bells and whistles. ECCV 2014. M. Mathias, R. Benenson, M. Pedersoli and L. Van Gool.
Paper: Face detection without bells and whistles. project:http://markusmathias.bitbucket.org/2014_eccv_face_detection/ Code:https://bitbucket.org/rodrigob/doppia Talk: http://videolectures.net/eccv2014_mathias_face_detection/(不错的报告) Slide:eccv2014_mathias_face_detection_01http://www.cvrobot.net/wp-content/uploads/2015/06/Face-detection-without-bells-and-whistles-1024x379.png 4:A Method for Object Detection Based on Pixel Intensity Comparisons Organized in Decision Trees. CoRR 2014. N. Markus, M. Frljak, I. S. Pandzic, J. Ahlberg and R. Forchheimer.
Code:https://github.com/nenadmarkus/pico Paper:Object Detection with Pixel Intensity Comparisons Organized in Decision Trees 实时人脸检测视频Demo:
5:Aggregate channel features for multi-view face detection.. B. Yang, J. Yan, Z. Lei and S. Z. Li. Paper: Aggregate channel features for multi-view face detection
3. 2015的最新进展 6:A Convolutional Neural Network Cascade for Face Detection. H. Li , Z. Lin , X. Shen, J. Brandt and G. Hua.
paper: A Convolutional Neural Network Cascade for Face Detection 7:Multi-view Face Detection Using Deep Convolutional Neural Networks. S. S. Farfade, Md. Saberian and Li-Jia Li 这是yahoo的人脸检测 Paper: Multi-view Face Detection Using Deep Convolutional Neural Networks News:The Face Detection Algorithm Set to Revolutionize Image Searchhttp://www.cvrobot.net/wp-content/uploads/2015/06/ICMR-2015-Multi-view-Face-Detection-Using-Deep-Convolutional-Neural-Networks-1.png 8:Face Detection with a 3D Model. A. Barbu, N. Lay, G. Gramajo.
paper:Face Detection with a 3D Model 结论:The 3D proposals are not perfectly aligned with the face keypoints, which results in a reduced accuracy in the high precision/very low false positive regime compared to other state of the art methods. However, in the regime of at least 0.1 false positives per image, it outperforms the cascade-based state of the art methods.
声明:如果转载了本文,也请注明转载出处:http://www.cvrobot.net/latest-progress-in-face-detection-2015/。如果您对该类型算法技术感兴趣,可以关注新浪微博:视觉机器人或者加入 QQ群:101371386您的关注是我们最大的努力源泉~~
页:
[1]