利用分形编码进行基于形状的图像检索

Shape-based Image Retrieval Using Fractal Coding

分形编码在图像压缩方面取得了很好的效果,同时也能够用于基于内容的图像检索。该文结合分形技术,提出了一种有效的抽取特征检索图像的新方法。针对目前基于形状的图像检索领域中存在的问题,首先提出了一种通过构造不规则区域的相似膨胀分形编码算法,该算法能获得较高的压缩比。在图像检索中,该算法用一新的方式提取形状特征,实现了基于该算法的图像检索操作。实验结果表明该文算法能较好地描述图像的形状及空间分布信息,明显地提高了检索效率及准确度。

Fractal coding has been proved useful for image compression,and it is also proved effective for content-based image retrieval.In this paper,using fractal technique,we present a novel and efficient scheme for feature extract-ing.According to the problem of content-based image retrieval,a similar extension fractal coding arithmetic by construct-ing irregular region is presented.The arithmetic can get high compress ratio.In image retrieval,the paper gives a new method to get shape character of image,and image retrieval operation based on the arithmetic is realized.Experiment re-sult shows that the arithmetic can describe shape and space information commendably,and retrieval efficiency and ve-racity are advanced obviously.