Tree-Shaped Sampling Based Hybrid Multi-Scale Feature Extraction for Texture Classification
Dongdong Ma, Ziqin Chen, Qingmin Liao · 2018
Efficiency, distinctiveness and robustness are three main goals for feature extractors in application of texture classification. In this paper, a new feature extractor is designed which aims to achieve these three goals simultaneously. The contributions are threefold. Firstly, a tree-shaped multi-scale sampling structure is proposed to acquire points distributed along two circles and one octagon. Secondly, four histogram vectors are obtained by quantizing the sampling values through a hybrid strategy. In order to suppress the noise, mean filtering is used as a preprocessing step and the four vectors are concatenated to form the discriminant vector. Thirdly, experiments are conducted on different datasets with several well-known feature extractors. The results show that the proposed method improves the classification accuracy effectively and robustly, while has a moderate complexity. The source code is available at: https://github.com/madd2014/TSSHM.