一种区域逐像素点肤色检测算法

详细信息    查看全文 | 推荐本文 |

英文篇名：Local Pixel Wise Skin Detection Algorithm Based on FPGA 作者：张晋 ; 庄再姣 ; 刘会刚 ; 刘艳艳 ; 耿卫东 英文作者：Zhang Jin;Zhuang Zaijiao;Liu Huigang;Geng Weidong;Key Laboratory of Photo-Electronics Information Science and Technique of Ministry of Education,Key Laboratory of Photo-Electronics Thin Film Devices and Technique of Tianjin,Institute of Photo-electronics Thin Film Devices and Technique, Nankai University; 关键词：皮肤识别 ; FPGA ; 色彩空间转换 ; 实时图像处理 英文关键词：skin detection;;FPGA;;color Space;;real-time image processing 中文刊名：NKDZ 英文刊名：Acta Scientiarum Naturalium Universitatis Nankaiensis 机构：南开大学光电子薄膜器件与技术研究所光电子薄膜器件与技术天津市重点实验室光电信息技术科学教育部重点实验室; 出版日期：2016-08-20 出版单位：南开大学学报(自然科学版) 年：2016 期：v.49 基金：国家自然科学基金青年科学基金(61401237) 语种：中文; 页：NKDZ201604007 页数：5 CN：04 ISSN：12-1105/N 分类号：40-44

摘要

提出了一种区域逐像素点检测的皮肤识别算法,采用皮肤颜色的聚类性分析方法,实现了人的肤色在YCb Cr空间的数学建模、特征分析和肤色识别.在满足实时性检测要求的前提下,利用彩色空间阈值比较法,在16×16个的图像局部区域内逐像素点进行肤色检测,不需要大量的图像数据存储空间,能够节省系统的硬件资源.仿真结果和FPGA硬件验证均表明,提出的区域逐像素点检测识别方法,便于硬件实现,相对于传统的皮肤识别算法,占用的存储资源更少,并能够满足实时性皮肤识别的要求.
        Local skin recognition algorithm detecting skin pixel by pixel was presented. This algorithm realized mathematical modeling, feature analysis and skin color detection in the YCb Cr space. It reliably recognizes 16 by 16 skin areas pixel by pixel in the video, which using threshold value comparison under the color space, and it can also meet the requirement of real-time detection without numerous hardware storage resources. The simulation results and verification based on FPGA shows that the proposed detection algorithms is easier to implement in hardware, use less storage resource compared with the traditional skin recognition algorithm. And it also could meet the requirement real-time skin detection.

引文

1陈锻生,刘政凯.肤色检测技术综述[J].计算机学报,2006,29(2):194-207.
    2 Yang M H,Kriegman D,Ahuja N.Detecting faces in images:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(1):34-58.
    3 Zhao W,Chellappa R,Phillips P J,et al.Face recognition:A literature survey[J].Acm Computing Surveys(CSUR),2003,35(4):399-458.
    4 Oliver Schwaneberg,Holger Steiner,Peter Haring Bolivar,et al.Design of an LED-based sensor system to distinguish human skin from workpieces in safety applications[J].Applied Optics,2012,51(12):1 865-1 871.
    5 Oliver N,Pentland A,Bérard F.Lafter:a real-time face and lips tracker with facial expression recognition[J].Pattern Recognition,2000,33(8):1 369-1 382.
    6 Mckenna S J,Morrison K.A comparison of skin history and trajectory-based representation schemes for the recognition of user-specified gestures[J].Pattern Recognition,2004,37(5):999-1 009.
    7 Phung S L,Bouzerdoum A,Chai S D.Skin segmentation using color pixel classification:analysis and comparison[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(1):148-154.
    8 黄海波,蒋伟荣,刘勇,等.基于SOPC的智能车辆道路识别与跟踪[J].仪器仪表学报,2012,33(2):321-326.
    9 朱波,汶德胜,王飞.改进的Bayer插值算法及其硬件实现[J].光电子·激光,2013,24(6):1 211-1 218.
    10 Rossotti H.Colour:Why the world isn't grey[M].New Jersey:Princeton University Press,1983.
    11 Angelopoulou E.Understanding the color of human skin[C/OL]//Proceedings of the SPIE Conference on Human Vision and Electronic Imaging VI(SPIE),San Jose,CA,January 20,2001.[2014-10-17].http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=903744.
    12 Hani K A M,Junita M S,Shahrel A S.Color space selection for human skin detection using color-texture features and neural networks[C/OL]//IEEE International Conference on Computer and Information Sciences(ICCOINS),Kuala Lumpur,Malaysia,June 3-5,2014.[2014-10-18].http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6868362.