Radar Images Categorization Based on Multilayer Perception
Radar images are usually polluted because of some objective factors. The paper develops a system automatically to tell them apart,which is composed of three parts: pre-processor with image smoothing,edge detection and contour tracing;features extraction according to arc lines,radial lines,noise areas and hot areas;classifiers based on an iterate learner using neural network of multilayer perception. Experimental results show that this system works well for solving the issue.
Radar images neural network multilayer perception iterate learner
Yue Sui
Department of Physics and Electronics,Minjiang College,Fuzhou 350001,China
国际会议
西安
英文
855-858
2011-12-23（万方平台首次上网日期，不代表论文的发表时间）