Evaluation of Face Recognition Methods

Sushma Jaiswal

Abstract


Face recognition is an example of advanced object recognition. The process is influenced by several factors such as shape, reflectance, pose, occlusion and illumination which make it even more difficult. Today there exist many well known techniques to try to recognize a face. We present to the reader an investigation into individual strengths and weaknesses of the most common techniques including feature based methods, PCA based eigenfaces, LDA based fisherfaces, ICA, Gabor wavelet based methods, neural networks and hidden Markov models. Hybrid systems try to combine the strengths and suppress the weaknesses of the different techniques either in a parallel or serial manner. Today there exist many well known techniques to try to recognize a face. Experiments done with implementations of different methods have shown that they have individual strengths and weaknesses. Hybrid systems try to combine the strengths and suppress the weaknesses of the different techniques either in a parallel or serial manner. The paper is to evaluate the different techniques and consider different combinations of these.
Here we compare or evaluate templates based and geometry based face recognition, also give the comprehensive survey based face recognition methods.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


© 2017 International Journal of Global Research in Computer Science (JGRCS)
Copyright Agreement & Authorship Responsibility