摘要
提出一个基于模糊逻辑的图像检索系统.该系统使用模糊语言变量描述图像特征之间的相似性程度,而非图像特征本身,使得图像相似性推理能以非线性方式进行;模糊规则建立在用户对对象的认知基础之上,能够反映用户主观感知.由于具有相似特征变化范围的不同对象可以适用于相同的规则,使得算法对检索图像的不同类别具有良好的鲁棒性.另外,提出一种改进的直方图——平均面积直方图,以提取色彩特征.实验结果表明了模糊检索系统的有效性与可行性.
A fuzzy logic-based image retrieval system is proposed. The fuzzy language variables are used to describe the similarity degree of image features, not the features themselves. Image similarity then can be deduced in a nonlinear manner. These rules embed user general perceptions of an object, by which subjectivity of human perception of image contents can be expressed. In particular, different objects with same feature variations can be dealt with same fuzzy rules. The fuzzy logic-based image retrieval system has a good robustness to image categories. Moreover, an improvement on the traditional histogram called the average area histogram （AAH） is proposed to represent color features. Experimental results show the feasibility and efficiency of the proposed scheme.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第12期1355-1359,1369,共6页
Control and Decision
基金
国家863计划项目(2002AA413420)
