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：473-480
出版社：Copernicus Publications
摘要：In the last twenty-five years a great number of vectorization methods were developed. In this paper we first give an overview about the most known methods, and then propose a vectorization algorithm based on Artificial Neural Network method. This algorithm is implemented by using C# programming language. Because distortions in size and location after vectorization are important for mapping applications, we tested our algorithm and software on a cadastral map. We also compared the results of our algorithm with the results of Sparse Pixel Vectorization (SPV) algorithm. Although SPV algorithm delivers better results, our algorithm also givesacceptable results, which are suitable for mapping purposes
关键词：Spatial Information Sciences; Analysis; Artificial_Intelligence; Accuracy; CAD; Image; Information; Tracking
