Classification of High-resolution Images with Local Binary Pattern and Convolutional Neural Network: An Advanced Study

It is very important to accurately classify high-resolution satellite images and to classify each section of the image separately. Complex patterns, on the other hand, are difficult to identify. To address this issue, the deep learning method is being used. The deep learning method’s goal is to extract a large number of features without requiring human intervention. Nonetheless, combining deep features with texture properties improves classification performance. The proposed system facilitates deep feature learning combined with texture-based classification. Local Binary Pattern (LBP) is used to extract textural features, whereas Convolutional Neural Network (CNN) is used to extract spatial features. The proposed system’s main goals are as follows: (1) to efficiently combine deep features with texture features. (2) To improve classification accuracy. (3) Correctly classify the remote sensing image’s land cover/land map area. The proposed method is put into action, and the results are scrutinized to ensure its efficacy. Experiment results show that when texture features are combined with a deep learning approach, classification performance improves.

Author (s) Details

Ms. T. Gladima Nisia
Department of CSE, AAA College of Engg. & Tech., Sivakasi, India.

Dr. S. Rajesh
Department of IT, Mepco Schlenk Engineering College, Sivakasi, India.

View Book :- https://stm.bookpi.org/NAER-V3/article/view/1848

Leave a Reply

Your email address will not be published. Required fields are marked *