Efficient data mining for local binary pattern in texture image analysis

作者：

Highlights：

• Improve the performance of local binary pattern in texture image analysis.

• Frequent pattern mining efficiently explores the high-dimensional feature space.

• Mutual information-based feature selection selects the most discriminative features.

• Maintains low computational complexity.

摘要

•Improve the performance of local binary pattern in texture image analysis.•Frequent pattern mining efficiently explores the high-dimensional feature space.•Mutual information-based feature selection selects the most discriminative features.•Maintains low computational complexity.

论文关键词：Local binary pattern,Frequent pattern mining,Texture image,Feature selection,Classification

论文评审过程：Available online 2 February 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.01.055