A new Feature Local Binary Patterns (FLBP) method

Document Type

Conference Proceeding

Publication Date

12-1-2012

Abstract

This paper presents a new Feature Local Binary Patterns (FLBP) that encodes the information of both local texture and features. The features are broadly defined by, for example, the edges, the Gabor wavelet features, the color features, etc. Specifically, a binary image is first derived by extracting feature pixels from a given image I, and then a distance vector field is obtained by computing the distance vector between each pixel and its nearest feature pixel defined in the binary image. Based on the distance vector field and the FLBP parameters, a FLBP representation of the given image I can be formed. Rather than the traditional LBP which only compares a pixel with the pixels in its own neighborhood, the FLBP can compare a pixel with the pixels in its own neighborhood as well as in other neighborhoods. We apply the FLBP to eye detection. The experimental results using the BioID database show that the FLBP method significantly improves upon the LBP method. The FLBP method displays superior representational power and flexibility to the LBP method due to the introduction of feature pixels as well as its parameters.

Identifier

84873280519 (Scopus)

ISBN

[9781601322258]

Publication Title

Proceedings of the 2012 International Conference on Image Processing Computer Vision and Pattern Recognition Ipcv 2012

First Page

1124

Last Page

1130

Volume

2

This document is currently not available here.

Share

COinS