基于肤色和支持向量机的人脸检测

人脸检测作为人脸识别系统的重要一环,越来越受到技术研究和商业应用的关注。针对人脸检测环境的复杂性,该文提出了基于肤色和支持向量机的人脸检测算法。该算法对于具有复杂背景信息的人脸彩色图像,采用肤色检测的方法进行肤色区域的分割并去除噪声干扰,然后使用支持向量机(SVM)对于类似肤色区域进一步检测并确定人脸区域。实验表明,结合肤色模型的快速检测和支持向量机的二次验证,该方法能提高人脸检测的准确性,并缩短检测时间。

Face Detection Based on Skin Color and Support Vector Machine

As the most important part of the face recognition system,face detection is becoming more and more popular in technical research and business application.For the complexity of face detection environment,this paper proposes a face detection algorithm which based on skin color and Support Vector Machines.For color picture of face which has complex background information,the algorithm uses skin color detection to divide area of skin color,and to wipe off the noise interference,then do further examination for the same area of skin color and confirm the face area used by Support Vector Machines.As the experiment shown,combing quick speed detection of skin color model with the quadratic verification of Support Vector Machines,the method can improve the reliability of face detection and cut down the detection time.