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
Recommended Citation
Gu, Jiayu and Liu, Chengjun, "A new Feature Local Binary Patterns (FLBP) method" (2012). Faculty Publications. 17908.
https://digitalcommons.njit.edu/fac_pubs/17908
