Scale Invariant Face Recognition with Gabor Wavelets and SVM
Putta Sujitha1, Venkatramaphanikumar S2, Krishna Kishore K V3
1Putta Sujitha, Department of Computer Science & Engineering, Vignan’s Foundation for Science, Technology & Research, Vadlamudi, Guntur (Andhra Pradesh), India.
2Venkatramaphanikumar S, Department of Computer Science & Engineering, Vignan’s Foundation for Science, Technology & Research, Vadlamudi, Guntur (Andhra Pradesh), India.
3Krishna Kishore K V, Department of Computer Science & Engineering, Vignan’s Foundation for Science, Technology & Research, Vadlamudi, Guntur (Andhra Pradesh), India.
Manuscript received on 12 February 2019 | Revised Manuscript received on 02 March 2019 | Manuscript Published on 08 June 2019 | PP: 100-104 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E10190275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Face recognition is one of the prominent and accosting research areas in Biometrics. Extraction of discriminating features ensures the higher recognition accuracy even with limited training data. In this work, a novel framework is proposed with state of methods include Gabor wavelets, principal component analysis and support vector machine. Gabor wavelet is applied to extract rotation and scale invariant features from the normalized face image. Further to reduce the number of features principal component analysis is applied. The reduced feature data is classified using support vector machine with RVF kernel. To evaluate the performance of the proposed work benchmark datasets like ORL, Grimace and AR face datasets are used. The proposed methods outperform the existing methods even with limited training.
Keywords: Face Recognition; Gabor Wavelet; Principal Component Analysis; Support Vector Machine.
Scope of the Article: Pattern Recognition