Novel color LBP descriptors for scene and image texture classification

Document Type

Conference Proceeding

Publication Date

12-1-2011

Abstract

Four novel color Local Binary Pattern (LBP) descriptors are presented in this paper for scene image and image texture classification with applications to image search and retrieval. The oRGB-LBP descriptor is derived by concatenating the LBP features of the component images in the oRGB color space. The Color LBP Fusion (CLF) descriptor is constructed by integrating the LBP descriptors from different color spaces; the Color Grayscale LBP Fusion (CGLF) descriptor is derived by integrating the grayscale-LBP descriptor and the CLF descriptor; and the CGLF+PHOG descriptor is obtained by integrating the Pyramid of Histogram of Orientation Gradients (PHOG) and the CGLF descriptor. Feature extraction applies the Enhanced Fisher Model (EFM) and image classification is based on the nearest neighbor classification rule (EFM-NN). The proposed image descriptors and the feature extraction and classification methods are evaluated using three grand challenge databases and are shown to improve upon the classification performance of existing methods.

Identifier

84864936279 (Scopus)

ISBN

[9781601321916]

Publication Title

Proceedings of the 2011 International Conference on Image Processing Computer Vision and Pattern Recognition Ipcv 2011

First Page

537

Last Page

543

Volume

2

This document is currently not available here.

Share

COinS