Effective 3D Face Recognition Technique Based on Gabor and LTP Features
M. Chandrakala1, S. Ravi2
1M. Chandrakala, Research Scholar, Bharathiar University, Coimbatore (Tamil Nadu), India.
2Dr. S. Ravi, Department of Computer Science Engineering and Technology, Pondicherry University, (Pondicherry), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 30 December 2018 | PP: 284-290 | Volume-8 Issue-2S, December 2018 | Retrieval Number: 100.1/ijeat.B10641282S18/18©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 evergreen research areas, owing to the increased applicability of the face recognition system in several real-time applications. Previously, 2D face recognition systems are employed to serve the purpose however, these systems suffer from several external environmental conditions. This drawback is addressed by the 3D face recognition system, which can withstand the adverse external environmental conditions. However, the 3D face recognition systems are very limited in the existing literature. Taking this as a challenge, this work presents a 3D face recognition system that relies on gabor and Local Ternary Pattern (LTP) features. The significant features are selected by means of Information Gain Ratio (IGR) and the Extreme Learning Machine (ELM) classifier is trained to classify between the human faces. The performance of the proposed approach is satisfactory in terms of accuracy, sensitivity and specificity rates.
Keywords: Face Recognition, LTP, Gabor, Classification.
Scope of the Article: Pattern Recognition