云南师范大学学报（自然科学版）2017，Vol.37Issue(5)：27-33,7.DOI:10.7699/j.ynnu.ns-2017-061
复杂背景下基于YCbCr颜色空间和Mini-Batch聚类的肤色检测
Skin Color Detection Based on YCbCr Color Space and Mini-Batch Clustering in Complex Background
摘要
Abstract
In this paper,we propose a skin color detection algorithm based on YCbCr color space and Mini-Batch clustering for color images in complex background.Firstly,the target image is converted to YCbCr color space,and statistical the color threshold of Gauss distribution model in Cb and Cr component;then using Mini-Batch clustering algorithm to segment skin color in Cb and Cr component,and using region merging and filtering area of skin color region segmentation,finally get the pure skin color area.Compared with the traditional algorithm,the simulation results show that this algorithm has good robustness to illumination changes in body image with complicated background,and it can get the skin region more complete and accurate;at the same time,the processing efficiency of algorithm for large size image is higher than the traditional color clustering detection algorithm.Our algorithm can improve the detection speed of 20％.关键词
Mini-Batch聚类/YCbCr颜色空间/肤色检测/聚类分割/区域归并Key words
Mini-Batch clustering/YCbCr color space/Skin detection/Region merging/Clustering segmention分类
信息技术与安全科学引用本文复制引用
陈涛,云利军,程飞燕,王坤..复杂背景下基于YCbCr颜色空间和Mini-Batch聚类的肤色检测[J].云南师范大学学报（自然科学版）,2017,37(5):27-33,7.基金项目
云南省科技惠民计划资助项目(2014RA042) （2014RA042）
云南师范大学研究生科研创新基金资助项目(2017069). （2017069）
