Texture Moment for Content-Based Image Retrieval
Texture Moment for Content-Based Image Retrieval
复制标题
DOI：
10.1109/icme.2007.4284698
复制
发表时间：
2007-07
期刊：
影响因子：
--
通讯作者：
Mingjing Li
中科院分区：
文献类型：
--
作者：
Mingjing Li
针对基于内容的图像检索，设计了一种新的纹理特征--纹理矩来表征灰度图像的纹理特征。首先，通过在像素的八个邻域上应用七个正交模板，为每个像素定义七个属性。模板是从局部傅里叶变换得到的。然后，对所有内部像素分别计算这7个属性的均值和变化量，形成14维特征向量。由于该特征与其他颜色特征具有很强的互补性，将其与颜色特征适当地结合在一起可能会产生良好的图像检索效果。因此，还提供了两种功能组合。通过对5000幅通用图像的实验，验证了本文提出的纹理矩特征和两种特征组合的有效性。
In this paper, a novel low-level feature, named texture moment, is designed to characterize the texture properties of grayscale images for content-based image retrieval. At first, seven attributes are defined for each pixel by applying seven orthogonal templates on its eight neighborhoods. The templates are derived from local Fourier transform. Then, the mean and variation of those seven attributes are calculated for all interior pixels respectively to form a 14-D feature vector. As this feature is highly complementary to other color features, properly combining it with color features together may produce good image retrieval results. Therefore, two feature combinations are also provided. Experiments on 5,000 general-purpose images demonstrate the effectiveness of the proposed texture moment feature and two feature combinations.