摘要
颜色和纹理是描述图像内容的两个重要视觉特征,提出了一种基于分块颜色矩和灰度共生矩阵相结合的图像检索方法。根据图像背景内容的差异,将图像分成大小相等的子块,通过HSV颜色空间非均匀量化,计算子块的颜色矩来描述图像的局部颜色特征。整体图像采用灰度共生矩阵作为其纹理特征。结合两者采用加权欧式距离计算图像相似度,从实验结果中得出该检索方法的有效性。
Color and texture are two important visual features of an image. An efficient image retrieval technique which uses segment color moment and gray level co-occurrence matrix is proposed. An image is partitioned into sub-blocks of equal size according to the different backgrounds. Color of each sub-block is extracted by quantifying the HSV color space into non-equal intervals and the local color feature is represented by calculating the color moment. Texture of the whole image is obtained by using gray level co-occurrence matrix. Euclidean distance with weights is used to calculate the similarity of the images in terms of the both combined features. The efficiency of the retrieval method is demonstrated with the results.
出处
《微计算机信息》
2012年第8期162-164,共3页
Control & Automation
关键词
图像检索
HSV模型
颜色矩
灰度共生矩阵
Image Retrieval
HSV Model
Color Moment
Gray Level Co-occurrence Matrix
