基于分形编码拓扑特性的图像检索

A Image Retrieval Model of Fractal-based Encoding Topological Characteristic

为了更有效、更准确地进行图像检索 ,提出了一种利用分形编码这项重要的拓扑特性来处理图像索引的新方法 ,即将图像经分形编码 ,首先得到每张图像的迭代函数 ,然后将其伴随图像存入数据库中 ,成为该图像的索引文件最后对数据库进行搜索时 ,则通过对此索引文件的比对来找出与查询图像相似的图像。反观使用其他方法建立的图像索引数据库 ,则无法证明其建立的索引文件具有上述特质。实验显示 ,图像经过分形编码所表现出的几何性质以及独特的有效性和鲁棒性 ,证明该方法是一个更有效率。

Fractal code is approved an effective method to compress digital image. It proposes a new method to analyze digital image retrieval by fractal iterative function system. By image fractal code and obtained its iterative function, then the image and its iterative function are saved database becoming index file of the image. When database is searched and image index file is compared so that user retrieval images similar to query image. The index files of based on fractal code have three characteristics, the first, similar images have similar iterative functions so can produce similar index files; the second, similar index files can retrieval similar images; the third, no similar images have no similar iterative functions, vice versa. Compare to other methods are used to create database, their index files have not these characteristics. The fractal code produces large of data and needs an effective method to retrieval. So it combines to fractal function information, based on discriminant analysis estimating images similarity, so that determine correlation sequence of all images in database similar to query image. Experiment shows this retrieval method specialties, efficiency and robustness.