基于HOG和SVM的双眼虹膜图像的人眼定位算法
|
摘要
针对近红外光下现有的人眼定位算法普遍存在准确性不高、泛化能力不佳等问题,提出了一种基于方向梯度直方图(HOG)和支持向量机(SVM)相结合的双眼虹膜图像的人眼定位算法。利用HOG提取虹膜图像的人眼特征,并结合SVM分类器对HOG特征进行训练从而实现人眼的精确定位。为了减少漏检和误检,进一步提高定位准确率,又提出了多级级联SVM分类器算法;另外针对近红外光线下虹膜图像独特的灰度分布特点,设计了一种图像预处理方法,能够显著提高人眼定位速度。在MIR2016和CASIA-IRIS-Distance数据集上的实验结果表明,基于HOG和SVM的双眼虹膜图像的人眼定位算法具有高准确率、强泛化能力和高实时性。
Aiming at the problems such as low accuracy and poor generalization ability of the existing human eye location algorithms under near infrared light, a human eye location algorithm based on Histogram Oriented Gradient(HOG)and Support Vector Machine(SVM)is proposed. HOG is used to extract the human eye features of iris images and the HOG features are trained by SVM classifier to locate human eyes. In order to further improve the accuracy and reduce the missing detection and false detection, a multi-level cascade SVM classifier algorithm is proposed. In addition, aiming at the unique grayscale distribution characteristics of iris images under near infrared light, an image preprocessing method is designed, which can significantly improve the positioning speed. The experimental results on MIR2016 and CASIA-IRISDistance dataset show that the human eye location algorithm based on HOG and SVM has high accuracy, strong generalization ability and high real-time performance.
Aiming at the problems such as low accuracy and poor generalization ability of the existing human eye location algorithms under near infrared light, a human eye location algorithm based on Histogram Oriented Gradient(HOG)and Support Vector Machine(SVM)is proposed. HOG is used to extract the human eye features of iris images and the HOG features are trained by SVM classifier to locate human eyes. In order to further improve the accuracy and reduce the missing detection and false detection, a multi-level cascade SVM classifier algorithm is proposed. In addition, aiming at the unique grayscale distribution characteristics of iris images under near infrared light, an image preprocessing method is designed, which can significantly improve the positioning speed. The experimental results on MIR2016 and CASIA-IRISDistance dataset show that the human eye location algorithm based on HOG and SVM has high accuracy, strong generalization ability and high real-time performance.
引文
[1]Daugman J.How iris recognition works[J].IEEE Transactions on Circuits and Systems for Video Technology,2004,14(1):21-30.
[2]Elsherief S M,Allam M E,Fakhr M W.Biometric personal identification based on iris recognition[C]//International Conference on Computer Engineering and Systems,2006:208-213.
[3]Zheng Ying,Wang Zengfu.Minimal neighborhood mean projection function and its application to eye location[J].Journal of Software,2008,19(9):2322-2328.
[4]张娜娜,马燕,苏桂莲.基于灰度投影函数的眼睛定位方法[J].计算机工程,2006,32(10):193-195.
[5]李爱平,魏江,郝思思.基于灰度投影与改进Hough变换的人眼定位算法[J].电子设计工程,2014,22(16):171-173.
[6]侯向丹,赵丹,刘洪普,等.基于积分投影和差分投影的人眼定位[J].计算机工程与科学,2017,39(3):534-539.
[7]Sobottka K,Pitas I.Face localization and facial feature extraction based on shape and color information[C]//Proceedings of 3rd IEEE International Conference on Image Processing,1996:483-486.
[8]史慧荣,张学帅,梁彦,等.一种改进的模板匹配眼睛定位方法[J].计算机工程与应用,2004,40(33):44-45.
[9]王江波,李绍文.基于AdaBoost算法和模板匹配的人眼定位[J].计算机测量与控制,2012,20(5):1347-1349.
[10]Sun Y,Wang X,Tang X.Deep convolutional network cascade for facial point detection[C]//Computer Vision and Pattern Recognition,2013:3476-3483.
[11]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001:511-518.
[12]王丽婷,丁晓青,方驰.基于随机森林的人脸关键点精确定位方法[J].清华大学学报(自然科学版),2009,49(4):543-546.
[13]Van Ginneken B,Frangi A F,Staal J J,et al.Active shape model segmentation with optimal features[J].IEEE Transactions on Medical Imaging,2002,21(8):924-933.
[14]Zhu Z,Ji Q,Fujimura K,et al.Combining Kalman filtering and mean shift for real time eye tracking under active IR illumination[C]//Proceedings IEEE International Conference on Pattern Recognition,2002:318-321.
[15]Chen X,Flynn P J,Bowyer K W.IR and visible light face recognition[J].Computer Vision and Image Understanding,2005,99(3):332-358.
[16]Wang P,Green M B,Ji Q,et al.Automatic eye detection and its validation[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:164.
[17]徐渊,许晓亮,李才年,等.结合SVM分类器与HOG特征提取的行人检测[J].计算机工程,2016,42(1):56-60.
[18]Yao C,Wu F,Chen H,et al.Traffic sign recognition using HOG-SVM and grid search[C]//2014 12th International Conference on Signal Processing(ICSP),2014:962-965.
[19]Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition,2005:886-893.
[20]Cao X,Wu C,Yan P,et al.Linear SVM classification using boosting HOG features for vehicle detection in low-altitude airborne videos[C]//IEEE International Conference on Image Processing,2011:2421-2424.
[21]Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[22]Llorca D F,Arroyo R,Sotelo M A.Vehicle logo recognition in traffic images using HOG features and SVM[C]//International IEEE Conference on Intelligent Transportation Systems,2013:2229-2234.
[23]Ding X,Xu H,Cui P,et al.A cascade SVM approach for head-shoulder detection using histograms of oriented gradients[C]//IEEE International Symposium on Circuits and Systems,2009:1791-1794.
[24]Yang J C,Everett M,Buehler C,et al.A real-time distributed light field camera[C]//Eurographics Workshop on Rendering,2002:77-86.
[25]范海菊,冯云芝,王涛,等.离焦模糊图像模糊半径检测的新方法[J].计算机应用,2012,32(7):1875-1878.
[26]Uijlings J R,Sande K E,Gevers T,et al.Selective search for object recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[27]Xiao Y,Lu C,Tsougenis E,et al.Complexity-adaptive distance metric for object proposals generation[C]//Computer Vision and Pattern Recognition,2015:778-786.
[2]Elsherief S M,Allam M E,Fakhr M W.Biometric personal identification based on iris recognition[C]//International Conference on Computer Engineering and Systems,2006:208-213.
[3]Zheng Ying,Wang Zengfu.Minimal neighborhood mean projection function and its application to eye location[J].Journal of Software,2008,19(9):2322-2328.
[4]张娜娜,马燕,苏桂莲.基于灰度投影函数的眼睛定位方法[J].计算机工程,2006,32(10):193-195.
[5]李爱平,魏江,郝思思.基于灰度投影与改进Hough变换的人眼定位算法[J].电子设计工程,2014,22(16):171-173.
[6]侯向丹,赵丹,刘洪普,等.基于积分投影和差分投影的人眼定位[J].计算机工程与科学,2017,39(3):534-539.
[7]Sobottka K,Pitas I.Face localization and facial feature extraction based on shape and color information[C]//Proceedings of 3rd IEEE International Conference on Image Processing,1996:483-486.
[8]史慧荣,张学帅,梁彦,等.一种改进的模板匹配眼睛定位方法[J].计算机工程与应用,2004,40(33):44-45.
[9]王江波,李绍文.基于AdaBoost算法和模板匹配的人眼定位[J].计算机测量与控制,2012,20(5):1347-1349.
[10]Sun Y,Wang X,Tang X.Deep convolutional network cascade for facial point detection[C]//Computer Vision and Pattern Recognition,2013:3476-3483.
[11]Viola P,Jones M.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001:511-518.
[12]王丽婷,丁晓青,方驰.基于随机森林的人脸关键点精确定位方法[J].清华大学学报(自然科学版),2009,49(4):543-546.
[13]Van Ginneken B,Frangi A F,Staal J J,et al.Active shape model segmentation with optimal features[J].IEEE Transactions on Medical Imaging,2002,21(8):924-933.
[14]Zhu Z,Ji Q,Fujimura K,et al.Combining Kalman filtering and mean shift for real time eye tracking under active IR illumination[C]//Proceedings IEEE International Conference on Pattern Recognition,2002:318-321.
[15]Chen X,Flynn P J,Bowyer K W.IR and visible light face recognition[J].Computer Vision and Image Understanding,2005,99(3):332-358.
[16]Wang P,Green M B,Ji Q,et al.Automatic eye detection and its validation[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:164.
[17]徐渊,许晓亮,李才年,等.结合SVM分类器与HOG特征提取的行人检测[J].计算机工程,2016,42(1):56-60.
[18]Yao C,Wu F,Chen H,et al.Traffic sign recognition using HOG-SVM and grid search[C]//2014 12th International Conference on Signal Processing(ICSP),2014:962-965.
[19]Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]//IEEE Conference on Computer Vision and Pattern Recognition,2005:886-893.
[20]Cao X,Wu C,Yan P,et al.Linear SVM classification using boosting HOG features for vehicle detection in low-altitude airborne videos[C]//IEEE International Conference on Image Processing,2011:2421-2424.
[21]Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[22]Llorca D F,Arroyo R,Sotelo M A.Vehicle logo recognition in traffic images using HOG features and SVM[C]//International IEEE Conference on Intelligent Transportation Systems,2013:2229-2234.
[23]Ding X,Xu H,Cui P,et al.A cascade SVM approach for head-shoulder detection using histograms of oriented gradients[C]//IEEE International Symposium on Circuits and Systems,2009:1791-1794.
[24]Yang J C,Everett M,Buehler C,et al.A real-time distributed light field camera[C]//Eurographics Workshop on Rendering,2002:77-86.
[25]范海菊,冯云芝,王涛,等.离焦模糊图像模糊半径检测的新方法[J].计算机应用,2012,32(7):1875-1878.
[26]Uijlings J R,Sande K E,Gevers T,et al.Selective search for object recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[27]Xiao Y,Lu C,Tsougenis E,et al.Complexity-adaptive distance metric for object proposals generation[C]//Computer Vision and Pattern Recognition,2015:778-786.
© 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 |