基于K均值聚类与肤色的人脸检测研究  

Face detection based on K-means clustering and the skin-color

作　　者：张申 黄庆梅[1] 孙丽佳 ZHANG Shen;HUANG Qingmei;SUN Lijia(National Specialized Laboratory of Color Science and Engineering,College of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学光电学院颜色科学与工程国家专业实验室,北京100081

出　　处：《光学技术》2022年第3期301-306,共6页Optical Technique

基　　金：国家自然科学基金资助项目(61975012)。

摘　　要：针对传统人脸检测中存在色偏所造成检测精度偏低,深度学习方法中通过训练大量数据来实现人脸检测而造成硬件要求高等问题。提出了训练简单的卷积神经网络来实现人脸和非人脸的判断,并利用白平衡算法来解决色偏的问题。将YCgCr颜色空间与K均值聚类的方法结合起来实现肤色检测,最后在肤色检测的基础上实现人脸检测。其精度相较于传统的人脸检测方法提升3%左右,速度比基于深度学习的人脸检测快2倍左右。In view of the low detection accuracy caused by color bias in traditional face detection,the deep learning method realizes face detection by training a large amount of data,resulting in high hardware requirements.A simple convolutional neural network is proposed for face and non-face recognition,and then white balance algorithm is used to solve the problem of color cast.Skin-Color detection was realized by combining YCgCr color space with K-means clustering.Finally,face detection is realized on the basis of skin color detection.Its accuracy is about 3%higher than the traditional face detection method,and its speed is about twice faster than the face detection based on deep learning.

关 键 词：肤色 人脸检测 卷积神经网络 K均值聚类 YCGCR颜色空间 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]