Research Article
LBP-Based Edge Information for Color Texture Classification
131 downloads
@INPROCEEDINGS{10.1007/978-3-030-30149-1_19, author={Duc Phan Van Hoai and Vinh Truong Hoang}, title={LBP-Based Edge Information for Color Texture Classification}, proceedings={Industrial Networks and Intelligent Systems. 5th EAI International Conference, INISCOM 2019, Ho Chi Minh City, Vietnam, August 19, 2019, Proceedings}, proceedings_a={INISCOM}, year={2019}, month={9}, keywords={LBP Neighbor-Center Different Image Color texture classification}, doi={10.1007/978-3-030-30149-1_19} }- Duc Phan Van Hoai
Vinh Truong Hoang
Year: 2019
LBP-Based Edge Information for Color Texture Classification
INISCOM
Springer
DOI: 10.1007/978-3-030-30149-1_19
Abstract
In this paper, we propose to extract two types of feature from Neighbor-Center Difference Image (NCDI). NCDI is a variant of Local Binary Pattern (LBP) and originally used as input for Convolutional Neural Network (CNN). NCDI is a high dimensional feature and thus histograms are extracted from these NCDI features to mainly store useful information for statistical analysis. Two types of histograms are extracted from NCDI and then concatenated to further capture useful information. Experimental results on several benchmark color texture datasets show that the proposed approaches outperform the original LBP with a large margin (in accuracy) on several benchmark color texture datasets.
Copyright © 2019–2024 ICST