Your Search Results

Use this resource - and many more! - in your textbook!

AcademicPub holds over eight million pieces of educational content for you to mix-and-match your way.

Experience the freedom of customizing your course pack with AcademicPub!
Not an educator but still interested in using this content? No problem! Visit our provider's page to contact the publisher and get permission directly.

Two Dimensional Orthogonal Wavelet Features for Image Representation and Recognition

By: Woo, W.L.; Mutelo, R.M.; Dlay, S.S.;

2007 / IEEE / 1-4244-0881-4

Description

This item was taken from the IEEE Conference ' Two Dimensional Orthogonal Wavelet Features for Image Representation and Recognition ' In this paper, a novel two dimensional orthogonal wavelet features (2DOWF) method is presented for image representation and face recognition. The 2DOWF method derives 2D orthogonal wavelet (Gabor or Log Gabor) features in the feature extraction stage and then develops the cosine matrix measure for classification in the pattern recognition stage. 2DOWF method operates on the spatial structure of the pixels that defines the image. The wavelet transformed face images exhibit strong characteristics of spatial locality, scale, and orientation selectivity. These images can, thus, produce salient local features that are most suitable for face recognition. The two dimensional reduction PCA was used to detect noise, redundant features and form a representation in which these features are reduced. Analysis on the ORL dataset shows that the 2D orthogonal Log Gabor features are more suitable for face recognition than the 2D orthogonal Gabor features and the 2DPCA representation with an accuracy of 98.0% compared to 92.5% and 90.5%.