Translator Disclaimer
17 December 2015 TS-MRF sonar image segmentation based on the levels feature information
Author Affiliations +
Proceedings Volume 9811, MIPPR 2015: Multispectral Image Acquisition, Processing, and Analysis; 98110N (2015)
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
According to traditional methods of image segmentation on sonar image processing with less robustness and the problem of low accuracy, we propose the method of sonar image segmentation based on Tree-Structured Markov Random Field(TS-MRF), the algorithm shows better ability in using spatial information. First, using a tree structure constraint two-valued MRF sequences to model sonar image, through the node to describe local information of image, hierarchy information establish interconnected relationships through nodes, at the same time when we describe the hierarchical structure information of the image, we can preserve an image’s local information effectively. Then, we define split gain coefficients to reflect the ratio that marking posterior probability division before and after the splitting on the assumption of the known image viewing features, and viewing gain coefficients of judgment as the basis for determining binary tree of node split to reduce the complexity of solving a posterior probability. Finally, during the process of image segmentation, continuing to split the leaf nodes with the maximum splitting gain, so we can get the splitting results. We add merge during the process of segmentation. Using the methods of region splitting and merging to reduce the error division, so we can obtain the final segmentation results. Experimental results show that this approach has high segmentation accuracy and robustness.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tao Wu, Ping Xia, Xiaomei Liu, and Bangjun Lei "TS-MRF sonar image segmentation based on the levels feature information", Proc. SPIE 9811, MIPPR 2015: Multispectral Image Acquisition, Processing, and Analysis, 98110N (17 December 2015);

Back to Top