Target Detection in Complex Background based on Fuzzy Enhanced Fractal Feature
Non-universality and fuzziness of fractal would bring detection error when utilizing fractal feature to detect target in complex background. In this paper, a novel target detection algorithm based on fuzzy enhanced fractal feature is proposed. After the fractal feature named area measurement was estimated according to self–similarity of fractal, the new membership function of fuzzy sets based on the threshold that determined by fractal feature was defined. Then, the fractal difference between target and background was increased by fuzzy enhancement transformation. On this basis, combing mathematical morphology operation with boundary and area feature of the target, the detection approach was given. The experimental results indicated the fractal fuzzy enhancement can enhance the fractal feature of image effectively and the drawbacks of traditional fuzzy enhancement methods are avoided. Through the detection approach based on enhanced fractal feature, the target can be detected in complex background correctly and reliably, and the capability of restraining noise is good in detection.
Kunhua Zhang Xuan Yang Li Zhang
College of Information Engineering,Shenzhen University,Guangdong Shenzhen 518060,P.R. China
国际会议
2009 IEEE International Conference on Information and Automation(2009年 IEEE信息与自动化国际学术会议)
珠海、澳门
英文
408-411
2009-06-22（万方平台首次上网日期，不代表论文的发表时间）