a robust face locater using wld and dog for sspp
K. R. Saranya,A. Usha Ruby,J. George Chellin Chandran
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:2 Issue:3 Year: 08 April,2014 Pages:219-228
Abstract
The technology is growing in a rapid manner. As the technology is growing, security is more important. The core objective of this project is to extract the facial features using the local appearance based method for the accurate face identification with single sample per person problem. Generally face recognition is done by using two approaches: Holistic method and Local appearance based method. The Local appearance based method detects facial features such as eyes, nose, mouth and chin and also detects properties of and relations (e.g. areas, distances, angles) between the features are used as descriptors for face recognition. This project proposed a feature extraction and face recognition approach based on Weber’s Local Descriptor (WLD) and Difference of Gaussian (DoG)for the SSPP. The Gabor filter is used to extract the hybrid features and the pyramids are generated after the face granulation. By this granulation, facial features are segregated at different resolutions to provide edge information, noise, smoothness, and blurriness present in a face image. In features extraction stage, WLD descriptor represents an image as a histogram of differential excitations and illumination changes, elegant detection of edges and powerful image representation. These combined features are useful to distinguish the maximum number of samples accurately and it is matched with already stored original face samples for identification. This proposed approach reduces the computation time and also increases the efficiency.
Kewords
Difference of Gaussian Weber Local Descriptor face granulation SSPP
Reference
[1]. Turk M, Pentland A, Neurosci J (1991) Eigenfaces for recognition. J CognNeurosci 3(1):71–86 [2]. Lawrence S, Lee Giles C, Tsoi A, Back A (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113 [3]. Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720 [4]. Liu C,Wechsler H (2002) Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition. IEEE Trans Image Process 11(4):467–476 [5]. Heisele P, Ho J, Wu X, Poggio T (2003) Face recognition: component-based versus global approaches. Comput Vis Image Underst 91(1):6–12 [6]. Wang X, Tang X (2004) A unified framework for subspace face recognition. IEEE Trans Pattern Anal Mach Intell 26(9):1222–1228 [7]. He X, Yan X, Hu Y, Niyogi P, Zhang H (2005) Face recognition using Laplacian faces. IEEE Trans Pattern Anal Mach Intell 27(3):328–340 [8]. Tan X, Chen S, Zhou ZH, Zhang F (2006) Face recognition from a single image per person: a survey. Pattern Recognit 39(1):1725–1745 [9]. Zhang B, Shan S, Chen X, GaoW(2009) Are Gabor phases really useless for face recognition? PAA Pattern Anal Appl 12(3):301–307 [10]. Jie Chen, Member, IEEE, Shiguang Shan, Member, IEEE, Chu He, Guoying Zhao, MattiPietika¨ inen, Senior Member, IEEE, Xilin Chen, Senior Member, IEEE, and Wen Gao, Fellow, IEEE,( 2010) WLD: A Robust Local Image Descriptor. IEEE transactions on pattern analysis and machine intelligence, vol. 32, no. 9. [11]. Jamal Shah, Muhammad Sharif, MudassarRaza, and Aisha Azeem Department of Computer Sciences, COMSATS Institute of Information Technology, Pakistan, A Survey: Linear and Nonlinear PCA Based Face Recognition Techniques [12]. K. Jaya Priya · R.S. Rajesh, Selective local texture features based face recognition with single sample per class, J BrazComputSoc (2012) 18:229–235DOI 10.1007/s13173-011-0049. [13]. C. He, T. Ahonen, and M. Pietika¨inen, “A Bayesian Local Binary Pattern Texture Descriptor, ”Proc. International Conference Pattern Recognition, 2008.
