基于游程编码的块边缘模式图像检索算法

Image retrieval of the block edge pattern based on run-length coding

提出一种利用块边缘模式来进行图像检索的方法。该方法对图像中每个8×8块分别提取其块边缘模式,然后利用游程编码的原理,用块边缘模式构成图像的特征向量,以便进行基于内容的图像检索。所有数据在DCT压缩域中进行处理,不需要解压缩,从而降低了计算复杂度。实验结果表明,该算法与传统的基于DCT域的图像检索方法相比,具有更好的图像检索性能。

A new image retrieval algorithm based on block edge patterns was proposed in this paper. Block edge patterns were extracted in each 8×8 block of an image. Then by following the principle of run-length coding, the features of an image were extracted by utilizing block edge patterns to implement content-based image retrieval inside image database. Because the edge orientation of each block can be estimated in DCT（Discrete Cosine Transform） without decompressing, computation complexity declined greatly. In comparison with current representative techniques, the experimental results demonstrate the proposed algorithm has better performance both in retrieval efficiency and effectiveness.