复杂背景下人脸检测的数学形态学运算方法

游亚平; 袁保宗

复杂背景下人脸检测的数学形态学运算方法

计量
- 文章访问数: 2393
- HTML全文浏览量: 137
- PDF下载量: 1169
- 被引次数: 0
出版历程
- 收稿日期: 2003-07-24
- 修回日期: 2004-02-24
- 刊出日期: 2004-12-19

Mathematical Morphology Appoach to Face Detection in Complex Background

摘要

摘要: 皮肤的颜色特性被广泛地应用于人脸检测和跟踪中，本文采用HSV空间与归一化RGB空间相结合的肤色模型，提取原始图像中的类肤色区域作为候选人脸目标；采用数学形态学算子，分别用来完成去除噪声和干扰，分离侯选目标，提取眼睛嘴巴孔洞，以及标示人脸轮廓等处理过程。大量实验表明，该方法能有效地剔除臂和手等非人脸肤色目标；能克服人脸遮挡，姿势和方向变化，大小差异，光照变化等造成的困难；该方法的计算开销较小，易于实现，适合快速人脸检测。
- 人脸检测; 肤色模型; 形态学算子
Abstract: Skin color character is widely used for face detection and face tracking. This paper construct a mixed model in both normalized RGB and HSV color space, which can be used to acquire possible skin regions in original image. It designs a sequential flexible morphology operators which can respectively eliminate noises and disturbances, separate face candidates, acquire eye and mouth hole, and gain contours of faces. The experimental results show that the proposed approach can not only effectively eliminate human hands and arms non-face objects in image, but also smooth away difficulties of face occlusion, pose and orientation, size difference and light variety. Furthermore, this approach is easy to implement, and its computational spending is relatively smaller. So it is suitable to fast face detection.

HTML全文

参考文献(1)

Tsapatsoulis N, Avrithis Y, Kollias S. Facial image indexing in multimedia databases. Pattern Analysis () Applications, 2001, 4(2/3): 234-241.[2]Chai D, Ngan K N. Face segmenttation using skin-color map in videophone applications[J].IEEE Transa. on Circuits and Systems for Video Technology.1999, 9(4):551-564[3]Chua Tat-Seng, Zhao Yunlong, Kankanhalli S. Detection of human faces in a compressed domain for video stratification. The Visual Computer, 2002, 18(2): 774-782.[4]Mao J, Yin B. A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template[J].Pattern Recognition.1999, 32(7):1237-1248[5]Edwards G J.[J].Taylor C J, Cootes T. Learning to identify and track faces in image sequences.Proc. Fifth IEEE Intl Conf. Computer Vision, Chicago, USA.1998,:-[6]Yang Ming-Hsuan, Krieman J, Narendra Ahuja. Detecting faces in images: A survey. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002, PAMI-24(1): 34-58.[7]Amit Y, Geman D, Jedynak B. Efficient focusing and face detection. Face recognition: From Theory to Applications, NATO ASI Series F, Berlin: Springer-Verlag, 1998, 163: 124-156.[8]Leung T K, Burl M C, Perona P. Propabilistic affine invariants for recognition. Proc. IEEE Conf.Computer Vision and Pattern Recognition, Chicago, USA, 1998: 678-684.[9]Dai Y, Nakano Y. Face-texture model based on SGLD and its applicaton in face detection in a color scene[J].Pattern Recognition.1996, 29(6):1007-1017[10]McKenna S, Raja Y, Gong S. Tracking color objects using adaptive mixture models. Image and Vision Computing, 1999, 17(3/4): 223-229.[11]McKenna S, Raja Y, Gong S. Object tracking using adaptive colour mixture models. In ACCV,HongKong, China, 1998, 1: 615-622.[12]Mensor B, Bruning M. Segmentation of Human Faces in Color Images[J].In Proc. Seventh IEEE Intl. Conf. on Image Processing and its Applications IPA99, Kobe, Japan.1999, 3:652-636[13]Sobottka K.[J].Pitas I. Face location and feature extraction based on shape and color information.IEEE Intl Conf. Image Processing, Lanssanne.1996,:-Yang J, Waibel A. A real-time face tracker. Third Workshop Applications of Computer Vision,Sarasota, FL, USA, 1996: 142-147.[14]Wang Y J, Yuan B Z. A novel approach for human faces detection from color images under complex background[J].Pattern Recognition.2001, 34(10):1983-1992[15]阮秋琦.数字图像处理学.北京:电子工业出版社,2001年1月第一版,第九章.[16]阿尔文.R.蒂利,著,朱涛,译.人体工程学图解.北京:中国建筑工业出版社,1998:30-25.

施引文献

资源附件(0)

访问统计