基于颜色相关图和纹理矩的图像检索  

IMAGE RETRIEVAL BASED ON COLOUR CORRELOGRAM AND TEXTURE MOMENT

作　　者：李永芳[1] 

机构地区：[1]电子科技大学计算机科学与工程学院,四川成都610065

出　　处：《计算机应用与软件》2011年第10期38-42,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(60702072)

摘　　要：基于内容的图像检索的关键就是准确地提取图像特征。目前常见的图像特征的分类有颜色、纹理和形状。提出了改进的图像相关图算法以及纹理矩算法,并采取有效的方法来结合这两种算法实现高效的图像检索,图像相关图不仅反映了图像的灰度统计信息,而且还反映了图像的空间特征和灰度的渐变度。纹理矩是通过计算图像局部区域的力矩来反映图像的纹理特征。二者相结合整合了图像颜色和纹理信息。实验证明,改进的图像相关图以及纹理矩算法优于传统算法,二者通过在有限的空间维度下的结合在很大程度上提高了检索精度。The key of content-based image retrieval is to extract image feature accurately,current classification of the common image features are colour,texture and shape.In this paper,we propose an improved image correlation and texture moment algorithm and take effective way to combine these two algorithms to implement the efficient image retrieval.Image correlation not only reflects the gray level statistics,but also reflects the spatial characteristics and the gradient diversification of gray level.Texture moment is a method of obtaining texture features directly from the gray-level image by computing the moments of the image in local regions.The combination of them two integrates the colour and texture information of the image.Experiments showed that the improved image correlation and texture moment algorithm is superior to the traditional algorithm,both on the limited space in the dimensions and a reasonable combination,the retrieval accuracy is greatly improved.

关 键 词：图像相关图 纹理矩 图像检索 颜色空间 特征向量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]