一种基于加权色彩直方图的快速图像检索方法

A Fast Image Retrieval Method Based on Weighted Chromaticity Histogram

传统的基于颜色直方图的彩色图像检索方法的缺陷非常明显·首先是数据存储和运算量大,更重要的是在光照条件改变的情况下,图像检索效果不理想·为克服此缺陷,提出了一种基于加权色彩直方图的快速图像检索方法,它利用光照不变性模型,消除光照变化对图像的影响,并对归一化后的二维色彩直方图图像在加权后进行子波变换和DCT压缩,其中根据色彩直方图图像的像素点对应色彩值在原始图像中所占的比例,对该像素点的灰度值进行加权·实验结果表明,此方法不仅检索效果比传统方法有所提高,同时图像检索的平均耗时也大大降低·

The disadvantages of the traditional color image retrieval method based on color histogram are the large data storage and high complexity of computation. And what＇s more, the retrieval results with the condition of different illumination are not good as expected. So a fast image retrieval method based on the weighted chromaticity histogram is proposed in this paper. The method eliminates the condition of illumination using the illumination invariance model. And the image of 2-dimensional chromaticity histogram after normalization is compressed by wavelet and DCT transform, where the gray value of its pixel has been weighted based on the proportion of the chromaticity represented by the pixel in the raw image. Experiments show that retrieval results using the method presented are improved. And the time taken in retrieval process is much shorter than that when using traditional methods.