An Effective Similarity Measurement Algorithm for Dominant Color Feature Matching in Image Retrieval
首发时间:2011-03-17
Abstract:For the reason that dominant colors can characterize color information of image region and can represent the image using fewer dimensions, dominant color feature is one of the widely used color features in image retrieval. The dominant color feature is extracted in HSV color space, and is combined with color distribution information. In this paper, a new similarity measurement algorithm based on block distance is proposed for dominant color matching. Our proposed algorithm not only takes the distance between dominant colors into account, but also the difference of the percentage of dominant colors. The average precision of our algorithm improves about 5% and about 14% respectively compared with block distance and Euclidean distance. Although the average precision of our algorithm is almost equal to quadratic form distance, the computation cost of our algorithm is obviously less than it.
keywords: image retrieval dominant color color space similarity measurement
点击查看论文中文信息
用于主颜色特征匹配的一种有效的相似性度量算法
摘要:由于少数几维主颜色就能用于表征图像,因此主颜色特征成为图像检索领域中常用的颜色特征之一。本文结合颜色的空间分布信息,在HSV颜色空间中提取了图像的主颜色特征,并提出了一种基于街区距离的相似性度量算法,用于主颜色特征的匹配。我们的算法在相似度匹配的过程中,不仅考虑了主颜色间的距离,而且将主颜色所占百分比的差值也考虑了进去。实验证明,我们的算法与街区距离和欧式距离相比,平均查准率分别提高了约5%和14%;与二次式距离相比,虽然两者的平均查准率基本相同,但是我们的计算量明显少很多。
论文图表:
引用
No.4415530571296129****
同行评议
共计0人参与
勘误表
用于主颜色特征匹配的一种有效的相似性度量算法
评论
全部评论0/1000