Robust skin detection in real-world images |
| |
| Affiliation: | 1. College of Information Science and Engineering, Ocean University of China, Qingdao, China;2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;3. Department of Electrical Engineering, Princeton University, NJ 08544, USA;4. Department of Automation, Tsinghua University, Beijing, China;5. Department of Computer Science, Tsinghua University, Beijing, China;6. Department of Computer, Shandong University, Weihai, China;1. Dept. of Computer Science and Information Engineering, National Central University, Jhongli, Taiwan, ROC;2. Research Center for Information Technology Innovation, Academia Sinica, Taiwan, ROC;3. Graduate Institute of Communication Engineering, National Chung Hsing University, Taichung, Taiwan, ROC;1. Video Technique Department, Alibaba.com, E10, 10th Floor, Shanghai Mart, 2299 West Yan’an Road, Shanghai 200336, China;2. Baidu.com, Beijing, China;3. Lenovo Research, Hong Kong;4. Tsinghua University, Beijing, China;5. University of Science and Technology China, Beijing, China;1. Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung 804, Taiwan;2. Department of Computer Science and Information Engineering, Asia University, Taichung 413, Taiwan;3. Dept. of Medical Research, China Medical University Hospital, China Medical University, Taichung, Taiwan;4. Research Center for Information Technology Innovation, Academia Sinica, Taipei 115, Taiwan;5. Graduate Institute of Communication Engineering, National Chung Hsing University, Taichung 402, Taiwan |
| |
| Abstract: | Human skin detection in images is desirable in many practical applications, e.g., human–computer interaction and adult-content filtering. However, existing methods are mainly suffer from confusing backgrounds in real-world images. In this paper, we try to address this issue by exploring and combining several human skin properties, i.e. color property, texture property and region property. First, images are divided into superpixels, and robust skin seeds and background seeds are acquired through color property and texture property of skin. Then we combining color, region and texture properties of skin by proposing a novel skin color and texture based graph cuts (SCTGC) to acquire the final skin detection results. Comprehensive and comparative experiments show that the proposed method achieves promising performance and outperforms many state-of-the-art methods over publicly available challenging datasets with a great part of hard images. |
| |
| Keywords: | Skin detection Skin color map (SCM) Skin texture map (STM) Skin color and texture based graph cuts (SCTGC) Skin seed determination Color property Texture property Region property |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
