A Rough Neurocomputing Approach for Illumination Invariant Face Recognition System
To surmount the issue of illumination variation in face recognition, this paper proposes a rough neurocomputing recognition system, namely, RNRS for an illumination invariant face recognition. The main focus of the proposed work is to address the problem of variations in illumination through the strength of the rough sets to recognize the faces under varying effects of illumination. RNRS uses geometric facial features and an approximation-decider neuron network as a recognizer. The novelty of the proposed RNRS is that the correct face match is estimated at the approximation layer itself based on the highest rough membership function value. On the contrary, if it is not being done at this layer then decider neuron does this against reduced number of sample faces. The efficiency and robustness of the proposed RNRS are demonstrated on different standard face databases and are compared with state-of-art techniques. Our proposed RNRS has achieved 93.56 % recognition rate for extended YaleB face database and 85 % recognition rate for CMU-PIE face database for larger degree of variations in illumination.
KeywordsRough sets Neurocomputing Illumination variation Face recognition
This project is supported by AICTE of India (Grant No: 8023/ RID/RPS-81/2010-11, Dated: March 31, 2011).
- 3.Xiaogang, W.S., Xiaoou, T.: Bayesian face recognition using gabor features. In: Proceedings of the ACM SIGMM Workshop, pp. 70–73 (2003)Google Scholar
- 7.Liu, C., Wechsler, H.: Probabilistic reasoning models for face recognition. In: Proceedings of Computer Vision and Pattern Recognition, pp. 827–832 (1998)Google Scholar
- 8.Sang-II, C., Chong-Ho, C.: An effective face recognition under illumination and pose variation. In: Proceedings of International Joint Conference on Neural Networks, pp. 914–919 (2007)Google Scholar
- 9.Howell, A., Buxton, H.: Face recognition using radial basis function neural networks. In: Proceedings of the British Machine Vision Conference, pp. 455–464 (1996)Google Scholar
- 13.Wang, H., Li, S.Z., Wang, Y.: Face recognition under varying lightening conditions using self quotient image. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition (FGR), pp. 819–824 (2004)Google Scholar
- 16.Singh, K.R., Zaveri, M.A., Raghuwanshi, M.M.: A robust illumination classifier using rough sets. In: Proceedings of Second IEEE International Conference on Computer Science and Automation Engineering, pp. 10–12 (2011)Google Scholar
- 19.de Solar, J.R., Quinteros, J.: Illumination compensation and normalization in eigen space-based face recognition: a comparative study of different pre-processing approaches. Comput. Vis. Graph. Image Process. 42, 342–350 (1999)Google Scholar
- 21.AT & T or ORL Face Database (2010). http://www.uk.research.att.com/facedatabase.html. Accessed July 2010