基于颜色扇形模型的图像检索  

Image Retrieval Based on Color Sector Model

作　　者：吴秋丽[1] 李太君[1] 

机构地区：[1]海南大学信息科学技术学院,海口570228

出　　处：《现代计算机》2009年第7期68-70,共3页Modern Computer

基　　金：海南省自然科学基金资助项目(No.807002)

摘　　要：全局颜色直方图所描述的是各种色彩在整幅图像中所占的比例,无法体现图像颜色的空间分布情况。在HSV颜色模型的基础上,把图像的色调、饱和度和亮度分量分别在径向和角度两个方向上投影,得到六个投影直方图。以这六个投影直方图的前三阶中心矩作为特征,提出了利用扇形模型进行图像检索的算法。实验结果表明,该算法计算简洁、检索速度快,具有较高的查全率和查准率。Description of the global color histogram can not reflect the spacial distributing information of colors. In order to remedy this defect, presents a new image retrieval algorithm based on image projection. The hue, saturation and intensity is projected respectively onto the radial and angle directions, and six projective histograms are obtained,then, take the first three central moments （mean, variance, skewness） of these six projective histograms as features to compute the distances between images. Experimental results show that this algorithm performs tersely and quickly and has better recall rate and precision.

关 键 词：图像检索 检索模型 颜色直方图 扇形模型 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]