A Novel Permutation Based Approach for Effective and Efficient Representation of Face Images under Varying Illuminations

Paramount importance for an automated face recognition system is the ability to enhance discriminatory power with a low-dimensional feature representation. Keeping this as a focal point, we present a novel approach for face recognition by formulating the problem of face tagging in terms of permutation. Using a fundamental concept that, dominant pixels of a person will remain dominant under varying illuminations, we develop a Permutation Matrix (PM) based approach for representing face images. The proposed method is extensively evaluated on several benchmark databases under different exemplary evaluation protocols reported in the literature. Experimental results and comparative study with state-of-the-art methods suggest that the proposed approach provides a better representation of face, thereby achieving higher efficacy and lower error rates.

@article{S2013,
  title     = {A Novel Permutation Based Approach for Effective and Efficient Representation of Face Images under Varying Illuminations},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {4},
  number    = {7},
  year      = {2013},
  publisher = {The Science and Information Organization},
  author    = {Shylaja S S and K N Balasubramanya Murthy and S Natarajan},
  doi       = {10.14569/IJACSA.2013.040712},
  url       = {https://doi.org/10.14569/IJACSA.2013.040712}
}