Fig 9 - uploaded by Sirshendu Arosh
Content may be subject to copyright.
Source publication
In this paper, we propose a novel method of face recognition. The method involves Curvelet Transform, Complete Local Binary Pattern (CLBP), PCA and SVM. Curvelet transform function is a multi resolution and directional method which is efficient in representing curve singularities and edges in an image.An image is decomposed into curvelet subbands o...
Similar publications
Citations
... Table 2 shows the recognition rate obtained with various noise levels. Recognition Accuracy (%) Eigenface [3] 92.20 LBP [6] 95.45 Curvelet + PCA [22] 96.60 Curvelet + LBP [23] 94.00 Curvelet + CLBP [24] 98.50 Our Approach 99.25 ...
... Among these techniques, the directly extracted features are used to recognize the face images. A real time face recognition using curvelet transform and complete loca1 binary pattern (CLBP) are proposed by Sirshendu Arosh et al. (2012), in which an image is decomposed into the curvelet sub-band components in three different resolutions and the descriptive feature sets are extracted using the CLBP method. In another related work, a facial expression recognition approach using curvelet based local binary patterns Saha et al. (2010) is proposed, which can recognize the facial expression better. ...
... However, in many real-world applications, the local structure is more important since its description can represent face characteristics more effectively than the global description in face recognition. So we decide to use the Locality Preserving Projection (LPP) (Sirshendu Arosh et al., 2012) to reduce the dimension of face image features. The complete derivation and theoretical justifications of LPP can be found in He and Niyogi (2003) and here we only give a brief introduction. ...
... The Laplacian matrix for a finite graph is analogous to the Laplace Beltrami operator on compact Riemannian manifolds. Belkin and Niyogi Belkin and Niyogi (2001) showed that the optimal map preserving locality can be found by solving an optimization problem on the manifold and the detailed LPP algorithm can be found in Sirshendu Arosh et al. (2012). ...
In this paper, we propose a new feature extraction approach for face recognition based on Curvelet transform and local binary pattern operator. The motivation of this approach is based on two observations. One is that Curvelet transform is a new anisotropic multi-resolution analysis tool, which can effectively represent image edge discontinuities; the other is that local binary pattern operator is one of the best current texture descriptors for face images. As the curvelet features in different frequency bands represent different information of the original image, we extract such features using different methods for different frequency bands. Technically, the lowest frequency band component is processed using the local binary pattern method, and only the medium frequency band components are normalized. And then, we combine them to create a feature set, and use the local preservation projection to reduce its dimension. Finally, we classify the test samples using the nearest neighbor classifier in the reduced space. Extensive experiments on the Yale database, the extended Yale B database, the PIE pose 09 database, and the FRGC database illustrate the effectiveness of the proposed method.
