Texture Recognition Method of Remote Sensing Landform Image Based on Multi-Scale Semi-Coupled Convolutional Sparse Coding
Remote sensing landform images usually contain a large amount of data,which is highly complex and diverse,making it difficult to capture texture information at different levels,thereby affecting recognition performance.Therefore,in order to improve the effectiveness of texture feature extraction and ensure recognition accuracy,multi-scale semi coupled convolutional sparse encoding was used to study the texture recognition of remote sensing topographic images.To remove noise from remote sensing landform ima-ges,enhance the overall quality of remote sensing landform images,use watershed algorithm to segment remote sensing landform im-ages,explore the differences in texture features of remote sensing landform images at different scales,effectively capture texture in-formation at different levels,and improve the recognition performance of texture in remote sensing landform images.Then,the gray level co-occurrence matrix(GLCM)is applied to obtain multi-scale texture features of remote sensing geomorphic images,and a semi coupled convolutional sparse encoding model is constructed to complete the learning of multi-scale texture feature extraction process and effective fusion of multi-scale texture features,in order to reduce redundant information and improve the accuracy of texture rec-ognition while maintaining feature richness.Select an appropriate classifier-Naive Bayes classifier and train it.Based on this,develop a remote sensing landform image texture recognition program,and execute the program to obtain the landform texture recognition re-sults.The test results show that the remote sensing landform image processing results obtained by the proposed method have high clarity and contrast,and the terrain texture feature extraction results are more complete and clear.The terrain texture recognition re-sults are consistent with the actual results,fully confirming that the proposed method has better application effect.
万方数据
维普
