【作者】 吴成玉； 邰晓英； 赵杰煜；

【机构】 宁波大学信息学院； 宁波大学信息学院计算机软件新技术国家重点实验室；

【摘要】 <正>1.引言传统的图像检索基于文本匹配方式,但目前计算机视觉技术还不成熟,达不到对图像描述性关键字的自动提取。因此,人们提出了基于内容的图像检索(CBIR)技术。这种技术由机器自动提取包含图像内容的可视特征:颜色、纹理、形状、对象的位置和相互关系等,对数据库中图像和查询图像在特征空间进行相似匹配,检索出与样本相似的图像。更多还原

【Abstract】 Content based image retrieval is an important and fascinating area of research,and the present explore focuses on the similarity matching of lower-features.In this paper,our methods for image retrieval using color and texture features are first discussed.The spatial color distribution is represented with the dominant color of partition and the texture features are calculated with the co-occurrence matrices.On the basis of using color and texture features separately,a new method for image retrieval using combined color and texture feature is proposed. Meanwhile,the technique of relevance feedback is used in the algorithm to enhance the effectiveness of retrieval.更多还原