期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2008
卷号：XXXVII Part B2
页码：109-114
出版社：Copernicus Publications
摘要：To extract rules for detecting edges, it is helpful to have some familiarity with different kinds of edges in order to construct a suitable characterization. Typically, researchers have characterized edges as a step function or as a slope between two flat regions. In reality however, edges may deviate from these cases in any number of manners, such as gradual in transition, between areas of non-uniform intensity, between areas of similar intensity, noisy, or any combination of these problems. Furthermore, effective edge detection must go beyond local shape characteristics to reflect structural constraints. Edges appear not only as a local phenomenon, but as part of larger structures which can also be characterized heuristically. Again, we argue that it is possible to express structural constraints heuristically in a systematic way. We employ fuzzy reasoning for these tasks because the nature of the data is indeterminate at a low- level stage of processing. This paper presents a new method applied to edge modeling based on cloud model. According to the characteristics of section plane of edge, three types edge can be classified, ladder, pulse and fastigium. According to the edge digital characteristics, we can extend the normal cloud model to multi-distributing cloud models, Γ cloud, triangle cloud, trapezoid cloud, etc.. The new edge models can represent the digital characteristics perfectly. The method has three steps: 1) Edge transitional region extracting, which formed by part of the pixels between the objective and background of image. 2) Cloud-core generating by digital characteristics of image. 3) Edge vector cloud generating by backward cloud generator. The edge cloud is not normal distributing cloud in most cases. Γ distributing, triangle distributing and trapezoid distributing or others are more popular in edge cloud. The method we develop is demonstrated by applying it to the problem of edge modeling, various performance studies testify that the method is both efficient and effective
关键词：Image; Edge; Model; Spectral; Fuzzy Logic; Cloud model
