摘要： 传统基于形状的图像检索方法检索效率较低，针对该问题，提出一种基于对象轮廓特征点的图像检索方法。利用Mean Shift算法提取感兴趣对象，以对象曲率的局部极值点作为特征点，并将对象表示为这些特征点的特征向量，定义检索对象与被检索对象特征向量间的距离匹配机制，实现对象的匹配或识别。实验结果表明，与传统方法相比，该方法具有较高的查全率和查准率。

关键词: 图像检索, Mean Shift算法, 对象轮廓, 曲率, 特征点

Abstract: Considering the problem of the image retrieval method based on shape, this paper proposes a novel method for image retrieval based on feature points of contour of an interesting object. Mean Shift algorithm is applied to extract an interesting object, then the local maximum points of curvature of the object contour are calculated and the object is described with its eigenvector comprised of these feature points. An effective matching mechanism based distance between the eigenvectors of a retrieve object and a retrieved object is used to carry out matching or recognition between two objects. Experimental results show that the proposed method has a higher recall and precision.

Key words: image retrieval, Mean Shift algorithm, object contour, curvature, feature point

中图分类号: 

• TP911.73