Face recognition based on extended separable lattice 2-D HMMS

This paper proposes an extension of separable lattice 2-D hidden Markov models (SL-HMMs) for dealing with image rotation and local deformation. It is important to reduce the effect of geometrical variations in image recognition, e.g., location, size, and rotation. SLHMMs are one of the most efficien...

Full description

Saved in:
Bibliographic Details
Main Authors: Kumaki, K., Nankaku, Y., Tokuda, K.
Format: Conference Proceeding
Language:English
Subjects:
Data models
Discrete cosine transforms
Face recognition
Hidden Markov models
Lattices
separable lattice 2-D HMMs
Training
variational EM algorithm
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an extension of separable lattice 2-D hidden Markov models (SL-HMMs) for dealing with image rotation and local deformation. It is important to reduce the effect of geometrical variations in image recognition, e.g., location, size, and rotation. SLHMMs are one of the most efficient structures to accomplish invariance to size and location variations. However, since SL-HMMs only have one state sequence in each direction, they cannot deal with rotation or local deformation. The proposed models have state sequences corresponding to all rows and columns of an input image, and the complicated state alignments can represent rotation and local deformation. The effectiveness of the proposed models was demonstrated in face recognition experiments.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2012.6288352