一种基于模糊量化直方图的图像检索方法

An image retrieval method based on fuzzy quantization histogram

颜色直方图是一种重要的基于颜色特征的图像检索方法。本文在颜色量化中引入模糊集合理论以描述与人类视觉认知相关的模糊概念,提出了基于人的主观感知的模糊颜色量化方法,以及相对应的模糊匹配准则。归纳实验结果证明该方法可以减小量化误差和适应人的感知模糊性,该方法具有广泛的适应性和进一步提高检索精度的可能。

Color histogram is an important method of image retrieval based on color feature. By introducing the Fuzzy Sets Theory, a fuzzy color quantization method based on the subjective perception of human is proposed to minimize color quantization error and adapt to the fuzziness of human perception. Based on the method, fuzzy quantization histogram is extracted for image retrieval, and a fuzzy measure method is proposed. Experimental results show the effectiveness of the quantization method and good performance of the image retrieval algorithm.