基于Retinex算法的光照变化条件下人脸识别研究

Research on face recognition under illumination variation based on Retinex algorithm

光照变化会对人脸识别结果产生干扰,导致当前光照变化人脸识别结果不理想,为了降低光照变化对人脸识别结果的不利影响,以提高光照变化人脸识别效果,设计了基于Retinex算法的光照变化条件下人脸识别方法。采用激光传感器采集光照变化下的人脸图像,并对人脸进行格式转换,然后采用Retinex算法对转换后的人脸图像进行增强操作,消除光照变化对人脸图像干扰,改善人脸图像质量,最后采用模式识别技术设计人脸图像识别的分类器,并与其他人脸图像识别方法进行了对比测试。实验结果表明,本方法消除了不同光照变化的干扰,提高了人脸图像亮度、对比度和熵值,相对于对比方法,本方法的人脸识别精度更高,精度平均值达到了96%,而且加快了人脸识别速度,具有比较明显的优越性。

Illumination change does not interfere with face recognition results,resulting in unsatisfactory face recognition results due to illumination change.In order to reduce the adverse impact of illumination change on face recognition and improve the effect of illumination change face recognition,a face recognition method under illumination change conditions based on Retinex algorithm is designed in this paper.The laser sensor is used to collect the face image under the change of illumination,and the format conversion of the face is carried out,and then the Retinex algorithm is used to enhance the converted face image,eliminate the interference of the lighting change on the face image,improve the quality of the face image,and finally use the pattern recognition technology to design the classifier of face image recognition,and compare and test it with other face image recognition methods.The experimental results show that this method eliminates the interference of different illumination changes and improves the brightness,contrast and entropy of face image.Compared with the comparison method,the face recognition accuracy of this method is higher,the average accuracy reaches 96%,and speeds up the face recognition speed,which has obvious advantages.