Cited 1 time in
Cited 2 time in
Illumination-Robust Face Recognition Approach Using Enhanced Preprocessing and Feature Extraction
- Illumination-Robust Face Recognition Approach Using Enhanced Preprocessing and Feature Extraction
- Kim, DJ[Kim, Dong-Ju]; Shon, MK[Shon, Myoung-Kyu]; Lee, S[Lee, Seungik]; Kim, E[Kim, Eunsu]
- DGIST Authors
- Kim, DJ[Kim, Dong-Ju]; Shon, MK[Shon, Myoung-Kyu]
- Issue Date
- Journal of Nanoelectronics and Optoelectronics, 11(2), 141-147
- Article Type
- Bins; Center-Symmetric Local Binary Patterns; Extraction; Face Recognition; Face Recognition Systems; Feature Extraction; Feature Extraction Techniques; Illumination Variation; Pattern Recognition; Pattern Recognition Systems; Pre-Processing; Principal Component Analysis; Recognition Accuracy; Recognition Algorithm; Two-Dimensional Principal Component Analysis
- This paper presents an enhanced facial preprocessing and feature extraction technique for an illuminationrobust face recognition system. Overall, the proposed face recognition system consists of a novel preprocessing descriptor, an illumination-robust feature descriptor, and a fusion module as sequential steps. In particular, the proposed system introduces an enhanced center-symmetric local binary pattern as preprocessing descriptor and a differential two-dimensional principal component analysis as feature descriptor to achieve performance improvement. To verify the proposed system, performance evaluation was carried out using various binary pattern descriptors and recognition algorithms on the extended Yale B database. As a result, the proposed system showed the best recognition accuracy of 99.03% compared to other approaches, and we confirmed that the proposed approach is effective for practical face recognition systems. © Copyright 2016 by American Scientific Publishers All rights reserved.
- American Scientific Publishers
- Related Researcher
There are no files associated with this item.
- Convergence Research Center for Future Automotive Technology1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.