Image recognition based on hidden Markov eigen-image models using variational Bayesian method
- Resource Type
- Conference
- Authors
- Sawada, Kei; Hashimoto, Kei; Nankaku, Yoshihiko; Tokuda, Keiichi
- Source
- 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2013 Asia-Pacific. :1-8 Oct, 2013
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Signal Processing and Analysis
Hidden Markov models
Bayes methods
Image recognition
Vectors
Maximum likelihood estimation
Graphical models
Lattices
- Language
An image recognition method based on hidden Markov eigen-image models (HMEMs) using the variational Bayesian method is proposed and experimentally evaluated. HMEMs have been proposed as a model with two advantageous properties: linear feature extraction based on statistical analysis and size-and-location-invariant image recognition. In many image recognition tasks, it is difficult to use sufficient training data, and complex models such as HMEMs suffer from the over-fitting problem. This study aims to accurately estimate HMEMs using the Bayesian criterion, which attains high generalization ability by using prior information and marginalization of model parameters. Face recognition experiments showed that the proposed method improves recognition performance.