基于卷积神经网络的人脸图像质量评价
|
摘要
针对人脸识别过程中人脸图像质量较低造成的低识别率问题,提出了一种基于卷积神经网络的人脸图像质量评价模型。首先建立一个8层的卷积神经网络模型,提取人脸图像质量的深层语义信息;然后在无约束环境下收集人脸图像,并通过传统的图像处理方法以及人工筛选进行过滤,得到的数据集用以进行模型参数的训练;其次通过在图形处理器(GPU)上加速训练,得到用于拟合人脸图像到类别的映射关系;最后将输入在高质量图像类别的概率作为图像的质量得分,建立人脸图像的质量打分机制。实验结果表明,与VGG-16网络相比,所提模型准确率降低了0.21个百分点,但是参数规模减小了98%,极大地提高了模型运算效率;同时所提模型在人脸模糊、光照、姿态和遮挡方面都具有较强的判别能力。因此,可将该模型应用在实时人脸识别系统中,在不影响系统运行效率的前提下提高系统的准确性。
Aiming at the low recognition rate caused by low quality of face images in the process of face recognition, a face image quality evaluation model based on convolutional neural network was proposed. Firstly, an 8-layer convolutional neural network model was built to extract deep semantic information of face image quality. Secondly, face images were collected in unconstrained environment, and were filtered by traditional image processing method and manual selecting, then the dataset obtained was used to train the model parameters. Thirdly, by accelerating training on GPU(Graphics Processing Unit), the mapping relationship of fitted face images to categories was obtained. Finally, the input probability of high-quality image category was taken as the image quality score, and the face image quality scoring mechanism was established. Experimental results show that compared with VGG-16 network, the precision rate of the proposed model is reduced by 0.21 percentage points, but the scale of the parameters is reduced by 98%, which greatly improves the efficiency of the model. At the same time, the proposed model has strong discriminant ability in aspects such as face blur, illumination, posture and occlusion. Therefore, the proposed model can be applied to real-time face recognition system to improve the accuracy of the system without affecting the efficiency.
Aiming at the low recognition rate caused by low quality of face images in the process of face recognition, a face image quality evaluation model based on convolutional neural network was proposed. Firstly, an 8-layer convolutional neural network model was built to extract deep semantic information of face image quality. Secondly, face images were collected in unconstrained environment, and were filtered by traditional image processing method and manual selecting, then the dataset obtained was used to train the model parameters. Thirdly, by accelerating training on GPU(Graphics Processing Unit), the mapping relationship of fitted face images to categories was obtained. Finally, the input probability of high-quality image category was taken as the image quality score, and the face image quality scoring mechanism was established. Experimental results show that compared with VGG-16 network, the precision rate of the proposed model is reduced by 0.21 percentage points, but the scale of the parameters is reduced by 98%, which greatly improves the efficiency of the model. At the same time, the proposed model has strong discriminant ability in aspects such as face blur, illumination, posture and occlusion. Therefore, the proposed model can be applied to real-time face recognition system to improve the accuracy of the system without affecting the efficiency.
引文
[1]徐晓艳.人脸识别技术综述[J].电子测试,2015(5X):30-35.(XU X Y.Survey of face recognition technology[J].Electronic Test,2015(5X):30-35.)
[2]DODGE S,KARAM L.Understanding how image quality affects deep neural networks[C]//Proceedings of the 2016 8th International Conference on Quality of Multimedia Experience.Piscataway,NJ:IEEE,2016:11-16.
[3]KARAHAN S,YILDIRUM M K,KIRTAC K,et al.How image degradations affect deep CNN-based face recognition?[C]//Proceedings of the 2016 International Conference of the Biometrics Special Interest Group.Piscataway,NJ:IEEE,2016:22-29.
[4]ISO/IEC 19794-5.Information technology-biometric data interchange formats-Part 5:face image data[S].New York:A-merican National Standard Institute,2001.
[5]ICAO 9303.International civil aviation organization:machine readable travel documents[S].[S.l.]:International Civil Aviation Organization,2006.
[6]BERRANI S A,GARCIA C.Enhancing face recognition from video sequences using robust statistics[C]//Proceedings of the 2005IEEE Conference on Advanced Video and Signal based Surveillance.Washington,DC:IEEE Computer Society,2005:324-329.
[7]YANG Z,AI H,WU B,et al.Face pose estimation and its application in video shot selection[C]//ICPR'04:Proceedings of the 17th International Conference on Pattern Recognition.Washington,DC:IEEE Computer Society,2004,1:322-325.
[8]GAO X,LI S Z,LIU R,et al.Standardization of face image sample quality[C]//Proceedings of the 2007 International Conference on Biometrics,LNCS 4642.Berlin:Springer,2007:242-251.
[9]SELLAHEWA H,JASSIM S A.Image-quality-based adaptive face recognition[J].IEEE Transactions on Instrumentation and Measurement,2010,59(4):805-813.
[10]WONG Y K,CHEN S K,MAU S,et al.Patch-based probabilistic image quality assessment for face selection and improved videobased face recognition[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition Workshops.Piscataway,NJ:IEEE,2011:74-81.
[11]HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[12]YI D,LEI Z,LIAO S C,et al.Learning face representation from scratch[J].ar Xiv Preprint,2014,2014:ar Xiv.1411.7923.
[13]PHILLIPS P J,MOON H,RIZVI S A,et al.The FERET evaluation methodology for face-recognition algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090-1104.
[14]ZHANG L,ZHANG L,LI L.Illumination quality assessment for face images:a benchmark and a convolutional neural networks based model[C]//Proceedings of the 2017 International Conference on Neural Information Processing,LNCS 10636.Berlin:Springer,2017:583-593.
[2]DODGE S,KARAM L.Understanding how image quality affects deep neural networks[C]//Proceedings of the 2016 8th International Conference on Quality of Multimedia Experience.Piscataway,NJ:IEEE,2016:11-16.
[3]KARAHAN S,YILDIRUM M K,KIRTAC K,et al.How image degradations affect deep CNN-based face recognition?[C]//Proceedings of the 2016 International Conference of the Biometrics Special Interest Group.Piscataway,NJ:IEEE,2016:22-29.
[4]ISO/IEC 19794-5.Information technology-biometric data interchange formats-Part 5:face image data[S].New York:A-merican National Standard Institute,2001.
[5]ICAO 9303.International civil aviation organization:machine readable travel documents[S].[S.l.]:International Civil Aviation Organization,2006.
[6]BERRANI S A,GARCIA C.Enhancing face recognition from video sequences using robust statistics[C]//Proceedings of the 2005IEEE Conference on Advanced Video and Signal based Surveillance.Washington,DC:IEEE Computer Society,2005:324-329.
[7]YANG Z,AI H,WU B,et al.Face pose estimation and its application in video shot selection[C]//ICPR'04:Proceedings of the 17th International Conference on Pattern Recognition.Washington,DC:IEEE Computer Society,2004,1:322-325.
[8]GAO X,LI S Z,LIU R,et al.Standardization of face image sample quality[C]//Proceedings of the 2007 International Conference on Biometrics,LNCS 4642.Berlin:Springer,2007:242-251.
[9]SELLAHEWA H,JASSIM S A.Image-quality-based adaptive face recognition[J].IEEE Transactions on Instrumentation and Measurement,2010,59(4):805-813.
[10]WONG Y K,CHEN S K,MAU S,et al.Patch-based probabilistic image quality assessment for face selection and improved videobased face recognition[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition Workshops.Piscataway,NJ:IEEE,2011:74-81.
[11]HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[12]YI D,LEI Z,LIAO S C,et al.Learning face representation from scratch[J].ar Xiv Preprint,2014,2014:ar Xiv.1411.7923.
[13]PHILLIPS P J,MOON H,RIZVI S A,et al.The FERET evaluation methodology for face-recognition algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090-1104.
[14]ZHANG L,ZHANG L,LI L.Illumination quality assessment for face images:a benchmark and a convolutional neural networks based model[C]//Proceedings of the 2017 International Conference on Neural Information Processing,LNCS 10636.Berlin:Springer,2017:583-593.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |