An Exploration of V-HOG on W-Quartette Space for Multi Face Recognition Issues

Illumination, Pose, and Expression variations are the major factors that put down the performance of face recognition system. This paper presents a dewy-eyed withal efficient hypothetical description for complex face recognition based on combination of w-Quartette Colorspace with Variant Hoglets (v-HOG) in sequel of our earlier work of fSVD [1]. Firstly, face image is mapped onto w-Quartette Colorspace to effectively interpret information existing in the image. Further variant Hoglet is employed to extract substantive features exhibiting linear properties to map line singularities and at the same time to derive tender features of face contortions. To foster the extracted features, the features are projected to a lower dimensional space for efficient face recognition. Five distinct distance measures are adopted as classifier to obtain appreciable recognition rate.

[1]  Belavadi Bhaskar,et al.  An Investigation of fSVD and Ridgelet Transform for Illumination and Expression Invariant Face Recognition , 2014, ISI.

[2]  Poonam Sharma,et al.  Efficient face recognition using wavelet-based generalized neural network , 2013, Signal Process..

[3]  Fei Wang,et al.  Face recognition using spectral features , 2007, Pattern Recognit..

[4]  Luis Torres,et al.  The importance of the color information in face recognition , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[5]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[6]  Claudio A. Perez,et al.  Methodological improvement on local Gabor face recognition based on feature selection and enhanced Borda count , 2011, Pattern Recognit..

[7]  Wenbin Zhang,et al.  Volume measure in 2DPCA-based face recognition , 2007, Pattern Recognit. Lett..

[8]  S. Ramachandran,et al.  Face recognition using transform domain feature extraction and PSO-based feature selection , 2014, Appl. Soft Comput..

[9]  Witold Pedrycz,et al.  Face recognition using decimated redundant discrete wavelet transforms , 2011, Machine Vision and Applications.

[10]  Daoqiang Zhang,et al.  (2D)2PCA: Two-directional two-dimensional PCA for efficient face representation and recognition , 2005, Neurocomputing.

[11]  Stefanos Zafeiriou,et al.  Principal component analysis of image gradient orientations for face recognition , 2011, Face and Gesture 2011.

[12]  Alejandro F. Frangi,et al.  Two-dimensional PCA: a new approach to appearance-based face representation and recognition , 2004 .

[13]  Ziqiang Wang,et al.  Multiple kernel local Fisher discriminant analysis for face recognition , 2013, Signal Process..

[14]  George Ghinea,et al.  Gradient-Orientation-Based PCA Subspace for Novel Face Recognition , 2014, IEEE Access.

[15]  Anastasios Delopoulos,et al.  Linear subspaces for facial expression recognition , 2014, Signal Process. Image Commun..

[16]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Haifeng Hu,et al.  ICA-based neighborhood preserving analysis for face recognition , 2008, Comput. Vis. Image Underst..

[18]  Shuai Wu.  Quaternion-based improved LPP method for color face recognition , 2014 .

[19]  Shengcai Liao,et al.  Kernel sparse representation with pixel-level and region-level local feature kernels for face recognition , 2014, Neurocomputing.

[20]  Yutaka Satoh,et al.  Robust face recognition using the GAP feature , 2013, Pattern Recognit..

[21]  N. Veeranjaneyulu,et al.  A novel face recognition system based on combining eigenfaces with fisher faces using wavelets , 2010, Biometrics Technology.