Improving Edge-detection Algorithm based on Fractional Differential Approach
Fractional differential approach can detect textural features of digital image, makes it non-linear enhancement and suppresses the noise to a certain extent And the traditional Roberts algorithm can locate relative accurately for edge detection, it could get thin but not clear enough edge, which is largely affected by noise. This paper mainly discusses how to use the advantages of fractional differential method to improve the shortcomings of Roberts. Firstly, both the Roberts and fractional differential theory are clearly explained respectively. Secondly, it discusses in detail the structures and parameters of 3*3 any order fractional differential mask on eight orientations. Lastly,it puts forward a new method based on combination fractional differential and Roberts operator. Experiments show that it can detect edges with high accuracy, more details, fine distinction. This also can provides reference for the thin edge needed detection in some specific applications.
fractional differential Roberts algorithm edgedetection fractional differential Mark gradient method
XueHui Chen XiangDong Fei
School of Computer Science and Technology Sichuan University Chengdu, China
国际会议
成都
英文
100-103
2010-12-17（万方平台首次上网日期，不代表论文的发表时间）