Simulation-Level Implementation of Face Recognition in Uncontrolled Environment
Humans rely on their visual ability to perceive and analyze the visual world. This ability if given to computers can yield scientific and relevant details about the things around us. Recognizing face under uncontrolled environment is still a challenging task, especially under head pose variation. Initially, the gesture containing test input face is estimated; it is then transformed into a reference pose which is already learnt. We have analyzed many existing available techniques for recognizing face for different gestures and proposed a novel system using a combination of support vector machine (SVM) and K-nearest neighbor (K-NN). The system is implemented using MATLAB and simulated using Modelsim. It has been tested on publicly available face databases under varying head poses. The proposed model was trained by randomly selecting 10 images, each of 12 unique individuals, thus 120 images were used for training. The system was then tested by considering 93 different poses of all the 12 unique individuals, thus 1116 images were used for testing. A demo code, along with train images, test images, and results obtained from the proposed system can be downloaded from http://goo.gl/S5ofYR.
KeywordsFace recognition K-Nearest neighbor Support vector machine
The proposed work was made possible because of the grant provided by Vision Group Science and Technology (VGST), Department of Information Technology, Biotechnology and Science and Technology, Government of Karnataka, Grant No. VGST/SMYSR/GRD-402/2014-15 and the support provided by Department of Electronics and Communication Engineering, Karunya University, Coimbatore, Tamil Nadu, India.
- 2.Tolba, A.S., El-Baz, A.H., El-Harby, A.A.: Face recognition: a literature review. Int. J. Signal Proc. 2(2), 88–103 (2006)Google Scholar
- 4.Lee, H.S., Kim, D.: Generating frontal view face image for pose invariant face recognition. PR Lett. 27(7), 747–754 (2006)Google Scholar
- 5.Zhao, S., Gao, Y.: Automated face pose estimation using elastic energy models. 18th ICPR, 4, 618–621 (2006)Google Scholar
- 6.Gong, S. McKenna, S., Collins, J.J.: An investigation into face poses distributions. In: FG. pp. 265 (1996)Google Scholar
- 7.Gründig, M., Hellwich, O.: 3D Head Pose Estimation with Symmetry Based Illumination Model in Low Resolution Video, pp. 45–53. DAGM, LNCS (2004)Google Scholar
- 8.Cootes, T.F., Walker, K., Taylor, C.J.: View-based active appearance models. In: Proceedings of the Fourth IEEE International Conference Automatic Face and Gesture Recognition, pp. 227–232 (2000)Google Scholar
- 9.Balasubramanian, V.N., Krishna, S., Panchanathan, S.: Person-independent head pose estimation using biased manifold embedding. EURASIP J. Adv. Signal Process. pp. 1–15 (2008) Google Scholar
- 12.Fernandes, S.L., Josemin Bala, G.: 3D and 4D face recognition: a comprehensive review. Recent Pat. Eng. 8(2), 112–119 (2014)Google Scholar
- 13.Fernandes, S.L., Josemin Balam, G.: Development and analysis of various state of the art techniques for face recognition under varying poses. Recent Pat. Eng. 8(2), 143–146 (2014)Google Scholar
- 16.Fernandes, S.L., Josemin Bala, G.: Recognizing facial images in the presence of various noises and blurring effects using gabor wavelets, DCT-neural network, hybrid spatial feature interdependence matrix. In: 2nd IEEE International Conference on Devices, Circuits and Systems (2014)Google Scholar