%A Qinggang Wu, Yilan Zhao, Qiuwen Zhang, and Bin Jiang %T Remote Sensing Image Classification based on Fusion of ATLTP and Tamura Texture Features %0 Journal Article %D 2020 %J Int J Performability Eng %R 10.23940/ijpe.20.01.p7.5966 %P 59-66 %V 16 %N 1 %U {https://www.ijpe-online.com/CN/abstract/article_4342.shtml} %8 2020-01-20 %X

Similar remote sensing image classification is often affected by complex backgrounds, illumination changes and noise interference. To improve the classification accuracy of similar remote sensing scenes, a novel image algorithm is proposed based on the fusion of global and local texture features. Specifically, the proposed algorithm is composed of three steps. Firstly, adaptive threshold local ternary pattern (ATLTP) and Tamura texture features of remote sensing images are extracted separately. Secondly, both texture features are fused together in a cascade manner to mitigate the interference of complex backgrounds in remote sensing images. Finally, on the basis of the fused texture features, the remote sensing images are classified by Support Vector Machine (SVM). To evaluate the performance of the proposed algorithm, extensive experiments are conducted on two standard remote sensing datasets of UC Merced Land-Use and NWPU-RESISC45. The effectiveness of the proposed algorithm is validated by the average classification accuracy improvement of 8.94%.