篇名 | A New Method of Image Classification Based on Weighted Center Symmetric Local Ternary Pattern Feature |
---|---|
卷期 | 26:3 |
作者 | Huang,Mingming 、 Mu,Zhichun 、 Zeng,Hui |
頁次 | 039-049 |
關鍵字 | WCS-LTP feature 、 sparse coding spatial pyramid matching 、 image classification 、 EI 、 MEDLINE 、 Scopus |
出刊日期 | 201510 |
Texture information is critical to the accuracy of image classification systems. In this paper, we propose a novel descriptor called weighted center symmetric local ternary pattern (WCS-LTP), constructed by using the CS-LTP variance of the local region as an adaptive weight to adjust the contribution of the CSLTP code in histogram calculation. Then, based on the proposed WCS-LTP descriptor, we introduce a new local WCS-LTP feature extraction approach. Compared with conventional local CS-LTP feature, our proposed WCS-LTP feature, which exploits the complementary information of local spatial pattern and local contrast, can better characterize the image local texture. Finally, WCS-LTP feature based sparse coding spatial pyramid matching (ScSPM) representation classification is proposed for image classification. Extensive experimental results demonstrate that the effectiveness of our proposed WCS-LTP feature based ScSPM representation classification algorithm.