The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors ...The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors to be invariant to illumination gradients,scaling,homogeneous illumination,and rotation.In this article,we devise a novel feature extraction methodology,which explores the effectiveness of Gabor filters coupled with Block Local Binary Patterns in designing such descriptors.We effectively exploit the illumination invariance properties of Block Local Binary Patterns and the inherent capability of convolutional neural networks to construct novel rotation,scale and illumination invariant features.The invariance characteristics of the proposed Gabor Block Local Binary Patterns(GBLBP)are demonstrated using a publicly available texture dataset.We use the proposed feature extraction methodology to extract texture features from Chromoendoscopy(CH)images for the classification of cancer lesions.The proposed feature set is later used in conjuncture with convolutional neural networks to classify the CH images.The proposed convolutional neural network is a shallow network comprising of fewer parameters in contrast to other state-of-the-art networks exhibiting millions of parameters required for effective training.The obtained results reveal that the proposed GBLBP performs favorably to several other state-of-the-art methods including both hand crafted and convolutional neural networks-based features.展开更多
This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><...This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this system can be updated via our custom-built standalone android app and automatic restarting of the training and recognition process with an updated database. Using our proposed algorithm, a real-time face recognition accuracy of 78.40% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 98.05% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px have been achieved using the LRD200 database containing 200 images per person. With 100 images per person in the database (LRD100) the achieved accuracies are 60.60% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 95% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px respectively. A facial deflection of about 30</span></span></span><span><span><span><span><span style="color:#4F4F4F;font-family:-apple-system, " font-size:16px;white-space:normal;background-color:#ffffff;"="">°</span></span><span> on either side from the front face showed an average face recognition precision of 72.25%-81.85%. This face recognition system can be employed for law enforcement purposes, where the surveillance camera captures a low-resolution image because of the distance of a person from the camera. It can also be used as a surveillance system in airports, bus stations, etc., to reduce the risk of possible criminal threats.</span></span></span></span>展开更多
A novel coding based method named as local binary orientation code (LBOCode) for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation inf...A novel coding based method named as local binary orientation code (LBOCode) for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation information is attained with a winner-take-all rule. Subsequently, the resulting orientation mapping array is operated by uniform local binary pattern. Accordingly, LBOCode image is achieved which contains palmprint orientation information in pixel level. Further we divide the LBOCode image into several equal-size and nonoverlapping regions, and extract the statistical code histogram from each region independently, which builds a global description of palmprint in regional level. In matching stage, the matching score between two palmprints is achieved by calculating the two spatial enhanced histograms' dissimilarity, which brings the benefit of computational simplicity. Experimental results demonstrate that the proposed method achieves more promising recognition performance compared with that of several state-of-the-art methods.展开更多
利用步态对个人身份进行识别已经受到越来越多生物识别技术研究者的重视。步态能量图(GEI-Gait Energy Image)是一种有效的步态表征方法,Gabor小波能提取不同方向、不同尺度空间频率特征,因此,首先利用Gabor小波提取步态能量图不同方向...利用步态对个人身份进行识别已经受到越来越多生物识别技术研究者的重视。步态能量图(GEI-Gait Energy Image)是一种有效的步态表征方法,Gabor小波能提取不同方向、不同尺度空间频率特征,因此,首先利用Gabor小波提取步态能量图不同方向、不同尺度的信息,得到其幅值谱图,再利用LBP来提取Gabor幅值谱图的局部信息,相对于LBP直接作用于步态能量图,能提取步态能量图更多方向、更多尺度的局部特征。最后,利用具有良好降维和辨识能力的辨识共同向量(DCV-Discriminant Common Vector)对提取的LBP特征进行维数约减和特征选择,只需利用简单的最近邻分类器就能取得较好的识别效果。该算法在中科院自动化所的CASIA数据库上面进行试验取得了较高的正确识别率。还针对步态识别中的小样本问题提出了一种样本扩充方法,解决了步态识别中的小样本问题,并提高了算法的识别率。展开更多
基金The authors extend their appreciation to the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number 7906。
文摘The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors to be invariant to illumination gradients,scaling,homogeneous illumination,and rotation.In this article,we devise a novel feature extraction methodology,which explores the effectiveness of Gabor filters coupled with Block Local Binary Patterns in designing such descriptors.We effectively exploit the illumination invariance properties of Block Local Binary Patterns and the inherent capability of convolutional neural networks to construct novel rotation,scale and illumination invariant features.The invariance characteristics of the proposed Gabor Block Local Binary Patterns(GBLBP)are demonstrated using a publicly available texture dataset.We use the proposed feature extraction methodology to extract texture features from Chromoendoscopy(CH)images for the classification of cancer lesions.The proposed feature set is later used in conjuncture with convolutional neural networks to classify the CH images.The proposed convolutional neural network is a shallow network comprising of fewer parameters in contrast to other state-of-the-art networks exhibiting millions of parameters required for effective training.The obtained results reveal that the proposed GBLBP performs favorably to several other state-of-the-art methods including both hand crafted and convolutional neural networks-based features.
文摘This research presents an improved real-time face recognition system at a low<span><span><span style="font-family:" color:red;"=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">resolution of 15 pixels with pose and emotion and resolution variations. We have designed our datasets named LRD200 and LRD100, which have been used for training and classification. The face detection part uses the Viola-Jones algorithm, and the face recognition part receives the face image from the face detection part to process it using the Local Binary Pattern Histogram (LBPH) algorithm with preprocessing using contrast limited adaptive histogram equalization (CLAHE) and face alignment. The face database in this system can be updated via our custom-built standalone android app and automatic restarting of the training and recognition process with an updated database. Using our proposed algorithm, a real-time face recognition accuracy of 78.40% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 98.05% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px have been achieved using the LRD200 database containing 200 images per person. With 100 images per person in the database (LRD100) the achieved accuracies are 60.60% at 15</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px and 95% at 45</span></span></span><span><span><span style="font-family:;" "=""> </span></span></span><span style="font-family:Verdana;"><span style="font-family:Verdana;"><span style="font-family:Verdana;">px respectively. A facial deflection of about 30</span></span></span><span><span><span><span><span style="color:#4F4F4F;font-family:-apple-system, " font-size:16px;white-space:normal;background-color:#ffffff;"="">°</span></span><span> on either side from the front face showed an average face recognition precision of 72.25%-81.85%. This face recognition system can be employed for law enforcement purposes, where the surveillance camera captures a low-resolution image because of the distance of a person from the camera. It can also be used as a surveillance system in airports, bus stations, etc., to reduce the risk of possible criminal threats.</span></span></span></span>
基金supported partly by the National Grand Fundamental Research 973 Program of China under Grant No. 2004CB318005the Doctoral Candidate Outstanding Innovation Foundation under Grant No.141092522the Fundamental Research Funds under Grant No.2009YJS025
文摘A novel coding based method named as local binary orientation code (LBOCode) for palmprint recognition is proposed. The palmprint image is firstly convolved with a bank of Gabor filters, and then the orientation information is attained with a winner-take-all rule. Subsequently, the resulting orientation mapping array is operated by uniform local binary pattern. Accordingly, LBOCode image is achieved which contains palmprint orientation information in pixel level. Further we divide the LBOCode image into several equal-size and nonoverlapping regions, and extract the statistical code histogram from each region independently, which builds a global description of palmprint in regional level. In matching stage, the matching score between two palmprints is achieved by calculating the two spatial enhanced histograms' dissimilarity, which brings the benefit of computational simplicity. Experimental results demonstrate that the proposed method achieves more promising recognition performance compared with that of several state-of-the-art methods.
文摘利用步态对个人身份进行识别已经受到越来越多生物识别技术研究者的重视。步态能量图(GEI-Gait Energy Image)是一种有效的步态表征方法,Gabor小波能提取不同方向、不同尺度空间频率特征,因此,首先利用Gabor小波提取步态能量图不同方向、不同尺度的信息,得到其幅值谱图,再利用LBP来提取Gabor幅值谱图的局部信息,相对于LBP直接作用于步态能量图,能提取步态能量图更多方向、更多尺度的局部特征。最后,利用具有良好降维和辨识能力的辨识共同向量(DCV-Discriminant Common Vector)对提取的LBP特征进行维数约减和特征选择,只需利用简单的最近邻分类器就能取得较好的识别效果。该算法在中科院自动化所的CASIA数据库上面进行试验取得了较高的正确识别率。还针对步态识别中的小样本问题提出了一种样本扩充方法,解决了步态识别中的小样本问题,并提高了算法的识别率。