人脸图像信息可用性影响因素的研究分析
|
摘要
传统的图像质量评估技术通常用于判断图像的整体质量,而不能有效地判断人脸图像信息的可用性。而人脸图像信息可用性评估在安防监控中具有很强的应用价值。提出了人脸图像信息可用性的概念,并提出了通过人脸识别算法来评估该可用性的度量方法。通过采用PCA人脸识别算法模拟仿真,定量地从原理上研究了影响人脸图像信息有用性的关键因素,并通过实验进行了验证。
Traditional IQA(Image Quality Assessment) is used to do assessment on a general level,but can't be used for face image quality assessment.However,assessment of face quality is needed in many applications such as surveillance video.The validity of face image is defined,and a method to assess face image using face recognition algorithm is proposed.And the key factors that affecting validity of face image are analyzed through experiment of PCA recognition algorithm in this paper.
Traditional IQA(Image Quality Assessment) is used to do assessment on a general level,but can't be used for face image quality assessment.However,assessment of face quality is needed in many applications such as surveillance video.The validity of face image is defined,and a method to assess face image using face recognition algorithm is proposed.And the key factors that affecting validity of face image are analyzed through experiment of PCA recognition algorithm in this paper.
引文
[1]杨慕星,孟放,姜秀华.不同分辨力视频之间的图像质量客观评价研究[J].电视技术,2009,33(5):103-105.
[2]高立发,徐静涛.基于自然场景统计的无参考图像质量评价算法[J].电视技术,2014,38(1):11-16.
[3]MITTAL A,MOORTHY A K,BOVDC A C.No-reference image quality assessment in the spatial domain[J].IEEE Trans.Image Processing,2012,21(12):4695-4708.
[4]TANG H,JOSHI N,KAPOOR A.Learning a blind measure of perceptual image quality[C]//Proc.IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI:IEEE Press,2011:305-312.
[5]YE P,DOERMANN D.No-reference image quality assessment using visual codebooks[C]//Proc.IEEE International Conference on Image Processing.[S.l.]:IEEE Press,2011:3129-3138.
[6]SHEN J,LI Q,ERLEBACHER G.Hybrid no-reference natural image quality assessment of noisy,blurry,JPEG2000,and JPEG images[J].IEEE Trans.Image Processing,2011,20(8):2089-2098.
[7]ITU-R,ITU-R Recommendation 500-5 method for the subjective assessment of the quality of television pictures[S].1992.
[8]闫娟,程武山,孙鑫.人脸识别的技术研究与发展概况[J].电视技术,2006,30(12):81-84.
[9]王文文,钱振兴,赵丽丽.基于平滑特性的压缩图像质量盲评估[J].电视技术.2013,37(2):91-94.
[10]AT&T Laboratories Cambridge.Face database[S].2002.
[2]高立发,徐静涛.基于自然场景统计的无参考图像质量评价算法[J].电视技术,2014,38(1):11-16.
[3]MITTAL A,MOORTHY A K,BOVDC A C.No-reference image quality assessment in the spatial domain[J].IEEE Trans.Image Processing,2012,21(12):4695-4708.
[4]TANG H,JOSHI N,KAPOOR A.Learning a blind measure of perceptual image quality[C]//Proc.IEEE Conference on Computer Vision and Pattern Recognition.Providence,RI:IEEE Press,2011:305-312.
[5]YE P,DOERMANN D.No-reference image quality assessment using visual codebooks[C]//Proc.IEEE International Conference on Image Processing.[S.l.]:IEEE Press,2011:3129-3138.
[6]SHEN J,LI Q,ERLEBACHER G.Hybrid no-reference natural image quality assessment of noisy,blurry,JPEG2000,and JPEG images[J].IEEE Trans.Image Processing,2011,20(8):2089-2098.
[7]ITU-R,ITU-R Recommendation 500-5 method for the subjective assessment of the quality of television pictures[S].1992.
[8]闫娟,程武山,孙鑫.人脸识别的技术研究与发展概况[J].电视技术,2006,30(12):81-84.
[9]王文文,钱振兴,赵丽丽.基于平滑特性的压缩图像质量盲评估[J].电视技术.2013,37(2):91-94.
[10]AT&T Laboratories Cambridge.Face database[S].2002.