【摘要】 本文讨论了基于内容的图像检索系统中特征提取的技术,并提出了一种基于图像中心加权特征提取算法,即对图像不同位置提取的特征采用不同的加权系数,越靠近图像中心加权系数越大。最后使用支持向量机技术作为图像分类器进行图像的检索。实验表明该系统能有效地检索大规模的图像数据库,并取得了比较好的效果。更多还原

【Abstract】 In this paper feature extraction techniques of content-based image retrieval(CBIR) are discussed,and propose a weighted feature extraction approach based on image center.The different feature weights are adopted in the different position when extracting image’s features,the more high weight the more close to the image center.Finally support vector machine(SVM) is used as the classifier to rank images.Experiment results show that this system can retrieves effectively images from a large image database,and achieves superior performance.更多还原