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.
引文
[1]LIU Y,LUO Y,ZHOU W,et al.Image-quality-based fusion approach for face recognition[C].//Image and Signal Processing(CISP).Chongqing,CHINA:IEEE,2012.
[2]ABAZA A,HARRISON M A,BOURLAI T.Quality metrics for practical face recognition[C].//Pattern Recognition(ICPR).Tsukuba:IEEE,2012.
[3]DE MARSICO M,NAPPI M,RICCIO D.Measuring measures for face sample quality[C].//Mi For'11 Proceedings of the 3rd international ACM workshop on Multimedia in forensics and intelligence.New York,NY,USA:ACM,2011.
[4]NASROLLAHI K,T M.Extracting a Good Quality Frontal Face Image From a Low-Resolution Video Sequence[J].IEEE Transactions on Circuits and Systems for Video Technology,2011,21(10):1353-1362.
[5]LUO W,WANG X,TANG X.Content-based photo quality assessment[C].//Computer Vision(ICCV).Barcelona:IEEE,2011.
[6]LI C,BOVIK A C,WU X.Blind image quality assessment using a general regression neural network[J].//Neural Networks.2011,22(5):793-799.
[7]WONG Y,CHEN S,MAU S,et al.Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition[C].//Computer Vision and Pattern Recognition Workshops(CVPRW).Colorado Springs,CO:IEEE,2011.
[8]沈兰荪,张菁,李晓光.图像检索与压缩域处理技术的研究[M].北京:人民邮电出版社,2008:107-121.SHEN LANSUN,ZHANG QING,LI XIAOGUANG.Image Retrieval And Compressed Domain Processing[M].Beijing:Post&Telecom Press,2008:107-121.
[9]HOU X,ZHANG L.Saliency detection:A spectral residual approach[C].//Computer Vision and Pattern Recognition.Minneapolis,MN:IEEE,2007.
[10]ACHNANTA R,ESTRADA F,WILS P,et al.Salient region detection and segmentation[M].GER:Springer,2008:66-75.
[11]ACHANTA R,HEMAMI S,et al.Frequency-tuned salient region detection[C].//Computer Vision and Pattern Recognition.Miami,FL:IEEE,2009.
[12]CHENG M,ZHANG G,MITRA N J,et al.Global contrast based salient region detection[C].//Computer Vision and Pattern Recognition(CVPR)Providence,RI:IEEE,2011.
[13]ZHAI Y,MUBARAK S.Visual attention detection in video sequences using spatiotemporal cues[C].//MULTIMEDIA'06 Proceedings of the 14th annual ACM international conference on Multimedia.New York,NY,USA:ACM,2006.
[14]PHILLIPS P J,WECHSLER H,HUANG J,et al.The FERET database and evaluation procedure for face-recognition algorithms[J].Image and Vision Computing,1998,16(5):295-306.
[15]C.E.Thomaz and G.A.Giraldi.A new ranking method for Principal Components Analysis and its application to face image analysis[J].Image and Vision Computing,2010,28(6):902-913.