A Bayesian Approach to Image Recognition Based on Separable Lattice Hidden Markov Models

Kei SAWADA  Akira TAMAMORI  Kei HASHIMOTO  Yoshihiko NANKAKU  Keiichi TOKUDA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.12   pp.3119-3131
Publication Date: 2016/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDP7112
Type of Manuscript: PAPER
Category: Pattern Recognition
Keyword: 
image recognition,  hidden Markov models,  separable lattice hidden Markov models,  Bayesian approach,  deterministic annealing,  

Full Text: PDF(972.5KB)>>
Buy this Article




Summary: 
This paper proposes a Bayesian approach to image recognition based on separable lattice hidden Markov models (SL-HMMs). The geometric variations of the object to be recognized, e.g., size, location, and rotation, are an essential problem in image recognition. SL-HMMs, which have been proposed to reduce the effect of geometric variations, can perform elastic matching both horizontally and vertically. This makes it possible to model not only invariances to the size and location of the object but also nonlinear warping in both dimensions. The maximum likelihood (ML) method has been used in training SL-HMMs. However, in some image recognition tasks, it is difficult to acquire sufficient training data, and the ML method suffers from the over-fitting problem when there is insufficient training data. This study aims to accurately estimate SL-HMMs using the maximum a posteriori (MAP) and variational Bayesian (VB) methods. The MAP and VB methods can utilize prior distributions representing useful prior information, and the VB method is expected to obtain high generalization ability by marginalization of model parameters. Furthermore, to overcome the local maximum problem in the MAP and VB methods, the deterministic annealing expectation maximization algorithm is applied for training SL-HMMs. Face recognition experiments performed on the XM2VTS database indicated that the proposed method offers significantly improved image recognition performance. Additionally, comparative experiment results showed that the proposed method was more robust to geometric variations than convolutional neural networks.