一种基于视觉注意模型的人脸图像评估算法

摘要

人脸识别受光照和姿态等影响。对人脸图像进行质量评估有利于在人脸识别过程中获得有利于识别的人脸图像。提出一种新的基于视觉注意模型的人脸图像质量评估方法。首先进行人脸检测获得人脸区域，然后对人脸区域分别进行眼睛检测和显著性检测，再根据所得到的眼睛区域和显著图计算左眼显著性和右眼显著性，最后计算双眼显著性，作为人脸图像质量。该方法计算简单，不需要参考图像。实验结果表明，该方法能对人脸图像质量进行正确评估，评估结果符合人眼的视觉注意。%Face recognition is influenced by illumination and posture.Face image quality assessment obtained in the process of face recognition is good for face image recognition.This paper proposes a new model based on visual attention to do quality assessment method.First,the face region is got by face detection,and then eyes detection and significance detection are conducted separately.According to the obtained eyes area and significant figure,the significant characteristics of the right eye and the left one are calculated and that of two eyes is used as a human face image quality.This method is simple and do not need the reference images.The test results show that the method can assess the face image quality correctly and the assessment results conform to the human eye visual attention.