Face recognition using survival exponential entropy: Based on Markov Random Field modeling

In this paper, a new method for face recognition is proposed based on Markov Random Fields (MRF) modeling. Constrains on image features as well as contextual relationships between them are explored and encoded into a cost function derived based on a statistical model of MRF. The face images are divided into salient regions, and the MRF model is used to represent the relationship between the regions and region ID´s. We use a new salient region detector based on the survival exponential entropy (SEE), the survival exponential entropy based normalized mutual information is proposed and integrated with the MRF model as the similarity measure to reflect the similarity between two facial images. The proposed method is evaluated and compared with several state-of-the-art face recognition methods, experiments demonstrate promising results.