Papers by Keyword: Face Recognition

Paper TitlePage

Authors: Ching Tang Hsieh, Chia Shing Hu, Meng Shian Shih
Abstract: Conventional 2D face recognition methods often struggle when a subject's head is turned even slightly to the side. In this study, a face recognition system based on 3D head modeling that is able to tolerate facial rotation angles was constructed by leveraging the Open source graphic library (OpenGL) framework. To minimize the extensive angle searching time that often occurs in conventional 3D modeling, Particle Swarm Optimization (PSO) was used to determine the correct facial angle in 3D. This reduced the angle computation time to 6 seconds, which is significantly faster than other methods. Experimental results showed that successful ID recognition can be achieved with a high recognition rate of 90%.
Authors: Dao Qing Sheng, Guo Yue Chen, Kazuki Saruta, Yuki Terata
Abstract: In this paper, an approach based on local curvature feature matching for 3D face recognition is proposed. K-L transformation is employed to adjust coordinate system and coarsely align 3D point cloud. Based on B-splines approximation, 3D facial surface reconstruction is implemented. Through analyzing curvature features of the fitted surface, local rigid facial patches are extracted. According to the extracted local patches, feature vectors are constructed to execute final recognition. Experimental results demonstrate high performance of the presented method and also show that the method is fairly effective for 3D face recognition.
Authors: D. Venkatakrishnan Ragu, C. Hariram, N. Anantharaj, A. Muthulakshmi
Abstract: In recent years, the 3-D face has become biometric modal, for security applications. Dealing with occlusions covering the facial surface is difficult to handle. Occlusion means blocking of face images by objects such as sun glasses, kerchiefs, hands, hair and so on. Occlusions are occurred by facial expressions, poses also. Basically consider two things: i) Occlusion handling for surface registration and ii). Missing data handling for classification. For registration to use an adaptively-selected-model based registration scheme is used. After registering occlusions are detected and removed. In order to handle the missing data we use a masking strategy call masked projection technique called Fisher faces Projection. Registration based on the adaptively selected model together with the masked analysis offer an occlusion robust face recognition system.
Authors: Hao Ge Zeng, Li Zhu Zhan, Xi Yang Yang
Abstract: A Mahalanobis distance based semi-supervised fuzzy clustering model is presented in this paper, whose objective function has a good explanation on how the labeled and unlabeled data are used in finding the underlying structure of matrix data. The iterative algorithm to solve this model is given. This algorithm can directly deal with matrix data like face images. We use 2DPCA on both row and column directions to reduce the dimension of image faces. The experimental result shows that using 2DPCA and semi-supervised algorithms can have a fairly good recognition rate if enough labeled data are given.
Authors: Bo Xia Zeng, Wen Feng Li
Abstract: The non-rigid 3D characters recovery technology for 2D images array is affected by background diversity, motion complexity, data losing and noise of feature points, so the recognition and recovery accuracy of facial features deformation is low. Due to the high error in traditional method, the paper puts forward a 3D facial recognition algorithm based on random images array, which converts the 2D features to 3D by nonlinear mapping, and completes the recognition on foundation of 3D geometric features distance. The experimental results show that the method effectively reduces error and improves recognition effects.
Authors: Zhuo Chen, Hai Bo Wu, Sheng Ping Xia
Abstract: In the ordinary video monitoring system, the whole small scene is usually observed by a stationary camera or a few stationary cameras, but the system can’t zoom and focus on the target of interest rapidly, and also can’t get the high resolution image of the target of interest in a far distance. Therefore based on the research of the dual-camera cooperation and a RSOM clustering tree and CSHG algorithm, a cooperative dual-camera system is designed to track and recognize a face quickly in a large-scale and far-distance scene in this paper, which is made up of a Stationary Wide Field of View (SWFV) camera and a Pan-Tilt-Zoom (PTZ) camera. In the meanwhile, the algorithm can ensure the real-time requirement.
Authors: Dan Zhou, Hai Yan Gao, Yun Jie Zhang
Abstract: Nonnegative Matrix Factorization (NMF) is among the most popular subspace methods, widely used in a variety of image processing problems. However, this approach is very time-consuming in face recognition due to the extreme high dimensionality of the original matrix. To remedy this limitation, this paper presents a Decorrelation-based NMF (DNMF) method. The proposed algorithm first takes into account the dimension reduction of the original matrix by preprocessing of decorrelation in spatial domain, and then uses nearest neighbor classifier on the reduced subspace. The developed algorithm has been applied for the ORL standard face image database. Experimental results demonstrate the validity of this method.
Authors: Dong Cheng Shi, Qing Qing Wang
Abstract: As the most successful method of linear distinguish, principal component analysis(PCA) method is widely used in identify areas, such as face recognition. But traditional PCA is influenced by light conditions, facial expression and it extracts the global features of the image, so the recognition rate is not very high. In order to improve more accurately identify facial features and extract local features which account for a larger contribution to the identification. This paper brings up a method of a block face recognition based on wavelet transform (WT-BPCA). In the algorithm, face images are done two-dimensional wavelet decomposition, then from which extract low frequency sub-images. According to different face area makes different contribution to recognition, we use sub-block PCA method. According to the contribution of the block recognition results generate weighting factors, the face recognition rate based on PCA is effectively improved. Finally we construct classification to recognite. Do experiments in the ORL face database. Results show that this method is superior to the method of the traditional PCA.
Authors: Yong Gang Li, Rong Zhu, Cong Cong Zhang, Xun Wei Gong
Abstract: A face recognition method on mobile terminals based on manifold learning was proposed. Firstly, the modified Snake model was set in order to improve the accuracy and effectiveness of facial feature point labeling. Then, the partial mapping method was carried out to map the face images to a subspace for further analysis. Finally, the nearest neighbor classifier was enhanced to show the recognition results. The experimental results indicate that the performance of this method is excellent. It is boasts a higher accuracy rate and bigger robustness than the ordinary methods.
Authors: Chen Chiung Hsieh, Wei Hsu Chen
Abstract: This paper proposed five new types of facial features for face recognition. Ada-boost is used to detect face firstly. False detected faces are removed by dynamic background modeling and skin color detection. Skewed face is also calibrated to achieve higher accuracy. Based on Active Shape Modeling, the five new types of facial features including gradient histograms of facial components, vertical/horizontal projection of facial edge points, signature of facial components, multiple vertical/horizontal line segments within facial shape, and face template could be extracted. According to the classification capability, features are associated with different weights while during matching. Nearest neighbor classifier is deployed for face recognition by using the averaged of feature points of a person as the center. The size of database is 200 people which are selected from the face databases of MIT and ESSEX. Five images per person were used for training and 491 images were tested. The recognition rate was 98.3% and the processing speed reached 220ms per frame on a general personal computer.
Showing 1 to 10 of 140 Paper Titles