基于重组DCT系数子带能量直方图的图像检索

Image Retrieval Based on Subband Energy Histograms of Reordered DCT Coefficients

现在许多图像采用JPEG格式存储,检索这些图像通常要先解压缩,然后提取基于像素域的特征矢量进行图像检索。己有文献提出直接在DCT域进行图像检索的方法,这样可以降低检索的时间复杂度。本文提出对JPEG图像的DCT系数利用多分辨率小波变换的形式进行重组,对整个数据库中所有图像的DCT系数重组得到的若干子带,分别建立子带能量直方图,而后采用Morton顺序建立每幅图像的索引,并采用变形B树结构组织图像数据库用于图像检索。

Now, a large number of images are compressed by the JPEG format. Hence, the image decompression of inverse DCT is needed to retrieval these images, and then extract feature vectors in the pixel domain to retrieval images. Many approaches have been proposed for image retrieval in the DCT domain, which can reduce computation complication. The aiticle proposes a method that reorder DCT coefficients using multiresolution wavelet transform, build subband energy histograms formed from reordered DCT coefficients of database images, then build indices of images by using Morton order and order database for indexing by using variant B-tree data structure.