Algorithms and Techniques used for 3D Face Recognition in the Presence of Expressions and Occlusion (ATFRPEO)
Thippeswamy G.1, Ambika G.N2, Vidya R.3
1Dr.Thippeswamy G., VTU, BMSIT, Bangalore, India.
2Ambika G. N, VTU, BMSIT, Bangalore, India.
3Vidya.R, VTU, BMSIT, Bangalore, India.
Manuscript received on December 05, 2013. | Revised Manuscript received on December 11, 2013. | Manuscript published on December 15, 2013. | PP: 33-38 | Volume-2 Issue-1, December 2013. | Retrieval Number: A0559122113
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: 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: The purpose of this study is to enhance the algorithms towards the development of an efficient three dimensional face recognition system in the presence of expressions as well as for occluded face. The overall aim is to analyze patterns of expressions based on techniques relating to feature distances and also to segment the human face into non-occluded and occluded part of the occluded human face image. Here we are using two steps the first step is to recognize the face in different patterns of expressions and the second step is recognizing the occluded face. The first process can be obtained by using Euclidean distances, geodesic distances and regression models. And the second process is obtained by using Mean Based Weight Matrix (MBWM) algorithm.
Keywords: Face Recognition; Feature Distances; Expressions; Regression Analysis, MBWM, support vector machine, SLBM, occlusion, LBP.