基于DCT压缩域的图像检索方法

Image Retrieval Based on DCT Compressed-Domain

本文提出了一种基于DCT(Discrete Cosine Transform)压缩域的图像检索方法.对于DCT编码的图像数据,在不需要完全解码的情况下,直接抽取图像的内容特征进行图像检索.首先,重组DCT域的频率系数,使其具有方向性、多分辨率等特点,并利用这些特点提取图像的大致轮廓.接着统计图像轮廓的连通直方图(CRH:Connected-RegionHistogram),进行图像检索.并利用DC图的灰度直方图对检索结果进行重新排序.这种检索方法对灰度、旋转、平移等都具有一定的鲁棒性,具有较好的检索效果.

In this paper,An image retrieval method is proposed based on DCT compressed-domain.With the partial decoding of DCT-encoded image data, the image features are extracted directly from the compressed domain. At first, reorder the DCT parameters in compressed-domain to get the directionality and multi-resolution for extracting the sketch of image. And then retrieved images by the CRH (Connected-Region Histogram) of image sketch. At last, we can sort the retrieved result by the gray histogram of DC map. The method is robust to gray,rotation,translation,and so on.The experimental results show that the proposed method is effective in image retrieval.