摘要
提出了一种新的基于目标区域综合特征的图像检索方法。该方法利用融合区域信息与边缘检测的图像分割算法提取可能的目标区域。在用户确定一个目标区域后,在图像目标区域中分别提取36维的颜色特征、4维的纹理特征和7维的形状特征,然后进行区域匹配。最后,按照相似度从大从小的顺序将对应的图像显示给用户。实验结果表明,在查准率-查全率性能上,该方法不仅优于单一特征的方法,而且比基于全局综合特征的图像检索性能更好。
A new image retrieval method based on integrated features of object region is put forward. This method first extracts the possible object regions using the proposed image segment algorithm which is hosed on the integration of region information and edge detection. After the objection region is confirmed by the user, the color features with 36 dimensions, the textures feature with 4 dimensions and the shape feature with 7 dimensions are extracted. Then, the procedure of region match is carried out. Finally, the retrieval result is listed to user by the descending order of similarity. The experiments show that, in terms of precision-recall, this method not only is better than other methods which use the only feature, but also achieves better performance than the method which uses the global integrated features.
出处
《微计算机信息》
2010年第17期214-216,211,共4页
Control & Automation
关键词
图像检索
图像分割
区域特征
区域匹配
image retrieval
image segmentation
region feature
region match
