DMCA
Markovian Mixture Face Recognition with Discriminative Face Alignment
BibTeX
@MISC{Zhao_markovianmixture,
author = {Ming Zhao and Google Inc and Tat-seng Chua},
title = {Markovian Mixture Face Recognition with Discriminative Face Alignment},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A typical automatic face recognition system is composed of three parts: face detection, face alignment and face recognition. Conventionally, these three parts are processed in a bottom-up manner: face detection is performed first, then the results are passed to face alignment, and finally to face recognition. The bottom-up approach is one extreme of vision approaches. The other extreme approach is topdown. In this paper, we proposed a Markovian stochastic mixture approach for combining bottom-up and top-down face recognition: face recognition is performed from the results of face alignment in a bottom-up way, and face alignment is performed based on the results of face recognition in a top-down way. By modeling the mixture face recognition as a stochastic process, the recognized person is decided probabilistically according to the probability distribution coming from the stochastic face recognition, and the recognition problem becomes that “who the most probable person is when the stochastic process of face recognition goes on for an infinite long duration”. This problem is solved with the theory of Markov chains by properly modeling the stochastic process of face recognition as a Markov chain. As conventional face alignment is not suitable for this mixture approach, discriminative face alignment is proposed. And we also prove that the Markovian mixture face recognition results only depend on discriminative face alignment, not on conventional face alignment. Our approach can surprisingly outperform the face recognition performance with manual face localization, which is demonstrated by extensive experiments. 1.
Keyphrases
face recognition discriminative face alignment markovian mixture face recognition face alignment stochastic process conventional face alignment markov chain face detection bottom-up approach probability distribution probable person markovian stochastic mixture approach stochastic face recognition mixture approach top-down face recognition extreme approach infinite long duration extensive experiment face recognition performance markovian mixture face recognition result vision approach mixture face recognition recognition problem bottom-up manner manual face localization typical automatic face recognition system bottom-up way top-down way
