基于Logistic回归和BPNN的二值人脸图像识别
|
摘要
针对人脸检测识别中受外在条件影响及低识别率的问题,提出一种基于二值图像的Logistic回归和反向传播神经网络BPNN(back-propagation neural network)的人脸识别方法。该算法将彩色图像被转换成灰度图像。使用低通滤波器去噪,将局部窗口标准偏差和自适应阈值应用于灰度图像,得到高质量的二值去噪图像,从中检测可能的人脸区域。使用最近邻居内插方法将其缩小,与每个缩小大小的图像相对应地创建人脸数据库。使用Logistic回归和BPNN来分类属于每个人的所有图像,并为每一类图像获得一个决策边界。图像尺寸的缩小最大限度地减少了逻辑回归和神经网络训练的计算空间和时间。实验结果表明,在FEI图像数据库上Logistic回归和反向传播神经网络的识别精度高达97.5%,优于其他识别算法的精度。
Face detection and recognition is affected by external conditions has low recognition rate.To solve this problem,we proposed a face recognition method based on binary image Logistic regression and back-propagation neural network(BPNN).The algorithm converted the color images to grayscale images.A low-pass filter was used to remove the noise.The local window standard deviation and adaptive threshold were applied to grayscale images so as to obtain high-quality binary denoised images from which possible face regions were detected.We adopted the nearest neighbor interpolation method to reduce them.A face database was created corresponding to each reduced-size image.We used Logistic regression and BPNN to classify all images belonging to each person,and obtained a decision boundary for each type of image.The reduction in image size minimized the computational space and time of logistic regression and neural network training.Experimental results show that the accuracy of Logistic regression and BPNN is as high as 97.5% in the FEI image database,which is better than the accuracy of other recognition algorithms.
Face detection and recognition is affected by external conditions has low recognition rate.To solve this problem,we proposed a face recognition method based on binary image Logistic regression and back-propagation neural network(BPNN).The algorithm converted the color images to grayscale images.A low-pass filter was used to remove the noise.The local window standard deviation and adaptive threshold were applied to grayscale images so as to obtain high-quality binary denoised images from which possible face regions were detected.We adopted the nearest neighbor interpolation method to reduce them.A face database was created corresponding to each reduced-size image.We used Logistic regression and BPNN to classify all images belonging to each person,and obtained a decision boundary for each type of image.The reduction in image size minimized the computational space and time of logistic regression and neural network training.Experimental results show that the accuracy of Logistic regression and BPNN is as high as 97.5% in the FEI image database,which is better than the accuracy of other recognition algorithms.
引文
[1]Schroff F,Kalenichenko D,Philbin J.Face Net:A unified embedding for face recognition and clustering[C]//IEEEConference on Computer Vision and Pattern Recognition.IEEE Computer Society,2015:815-823.
[2]蔡芬.一种基于人工免疫的小波特征集合最近邻人脸识别算法[J].西南师范大学学报(自然科学版),2016,41(3):96-100.
[3]Zhu X,Lei Z,Yan J,et al.High-fidelity pose and expression normalization for face recognition in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:787-796.
[4]Sariyanidi E,Gunes H,Cavallaro A.Automatic analysis of facial affect:A survey of registration,representation,and recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(6):1113-1133.
[5]Ding C,Choi J,Tao D,et al.Multi-directional multi-level dual-cross patterns for robust face recognition[J].IEEEtransactions on pattern analysis and machine intelligence,2016,38(3):518-531.
[6]Lu J,Liong V E,Zhou X,et al.Learning compact binary face descriptor for face recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(10):2041-2056.
[7]Majumder A,Behera L,Subramanian V K.Emotion recognition from geometric facial features using self-organizing map[J].Pattern Recognition,2014,47(3):1282-1293.
[8]Ghimire D,Lee J,Li Z N,et al.Recognition of facial expressions based on salient geometric features and support vector machines[J].Multimedia Tools and Applications,2017,76(6):7921-7946.
[9]李忠健,杨宜民,梅平.基于改进的隐马尔科夫模型的人脸识别方法[J].工业控制计算机,2014,27(11):29-31.
[10]朱黎,胡涛,罗锋.基于自适应LBP人脸识别的身份验证[J].计算机工程与科学,2014,36(11):2217-2222.
[11]张辉,刘新.基于改进LBP的单样本人脸识别算法[J].计算机应用与软件,2017,34(12):220-223,282.
[12]He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Las Vegas,NV,United States:IEEE,2016:770-778.
[13]Wen Y,Zhang K,Li Z,et al.A discriminative feature learning approach for deep face recognition[C]//European Conference on Computer Vision.Springer,Cham,2016:499-515.
[14]Ding C,Tao D.Robust face recognition via multimodal deep face representation[J].IEEE Transactions on Multimedia,2015,17(11):2049-2058.
[2]蔡芬.一种基于人工免疫的小波特征集合最近邻人脸识别算法[J].西南师范大学学报(自然科学版),2016,41(3):96-100.
[3]Zhu X,Lei Z,Yan J,et al.High-fidelity pose and expression normalization for face recognition in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:787-796.
[4]Sariyanidi E,Gunes H,Cavallaro A.Automatic analysis of facial affect:A survey of registration,representation,and recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(6):1113-1133.
[5]Ding C,Choi J,Tao D,et al.Multi-directional multi-level dual-cross patterns for robust face recognition[J].IEEEtransactions on pattern analysis and machine intelligence,2016,38(3):518-531.
[6]Lu J,Liong V E,Zhou X,et al.Learning compact binary face descriptor for face recognition[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(10):2041-2056.
[7]Majumder A,Behera L,Subramanian V K.Emotion recognition from geometric facial features using self-organizing map[J].Pattern Recognition,2014,47(3):1282-1293.
[8]Ghimire D,Lee J,Li Z N,et al.Recognition of facial expressions based on salient geometric features and support vector machines[J].Multimedia Tools and Applications,2017,76(6):7921-7946.
[9]李忠健,杨宜民,梅平.基于改进的隐马尔科夫模型的人脸识别方法[J].工业控制计算机,2014,27(11):29-31.
[10]朱黎,胡涛,罗锋.基于自适应LBP人脸识别的身份验证[J].计算机工程与科学,2014,36(11):2217-2222.
[11]张辉,刘新.基于改进LBP的单样本人脸识别算法[J].计算机应用与软件,2017,34(12):220-223,282.
[12]He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Las Vegas,NV,United States:IEEE,2016:770-778.
[13]Wen Y,Zhang K,Li Z,et al.A discriminative feature learning approach for deep face recognition[C]//European Conference on Computer Vision.Springer,Cham,2016:499-515.
[14]Ding C,Tao D.Robust face recognition via multimodal deep face representation[J].IEEE Transactions on Multimedia,2015,17(11):2049-2058.