基于支持向量机的语义图像分类研究

Research of Semantic Image Classification Based on Support Vector Machine

随着多媒体数据库的不断发展,传统的利用关键词进行图像检索已经越来越不能满足图像检索的需要,基于内容的图像检索已成为当前的研究热点。对图像的颜色和纹理特征进行提取,融合图像的颜色和纹理特征作为图像的特征向量,用支持向量机实现图像的低层特征和高级语义间的关联。实验结果表明,多特征的图像检索要比单一的特征检索效果好,在HSV颜色特征的基础上引入灰度共生矩阵纹理特征后可有效提高检索效率,而且采用支持向量机融合多特征可成功用于图像的语义的检索。

With the continually development of multimedia database, traditional image retrival method which is based on keywords can not satisfy most of the requirement of image retrieval. In recent years, more and more researchers have transferred their focus of scientific researches on content - based image retrieval. Extract the color and texture feature of the image, integrate color feature and texture feature as the feature vectors. Use support vector machine correlating image lov-level feature with high- level semantic. Experimental result shows that, the retrieval of image with multiple features is better than that of image with single feature. The introduction of gray scale texture feature into HSV color feature can improve the efficiency of image retrieval. Furthermore, support vector machine can be successfully used in image semantic retrieval.