Fast JPEG Image Retrieval Based on AC Huffman Tables
Fast JPEG Image Retrieval Based on AC Huffman Tables
复制标题
DOI：
10.1109/sitis.2013.16
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
G. Schaefer;David Edmundson;Yoshitaka Sakurai
中科院分区：
文献类型：
--
作者：
G. Schaefer;David Edmundson;Yoshitaka Sakurai
网络上的视觉信息，特别是图像形式的信息，正在快速增加。因此，人们寻求高效且有效的视觉信息检索技术，特别是因为用户很少对图像进行注释。在本文中，我们提出了一种非常快速的基于内容的 JPEG 压缩图像图像检索方法。我们的方法直接在 JPEG 压缩域中工作，并且仅基于图像标头中可用的信息。我们利用 JPEG 用于熵编码的霍夫曼表可以进行优化以最大化压缩这一事实。由于该过程使霍夫曼表适应图像内容，因此我们直接利用这些表，特别是AC亮度和色度表条目的前缀码长度作为图像特征，并采用码长向量之间的L1距离作为相似性度量。我们在超过 100 万张图像的不同大小的基准数据库上评估了我们的方法，结果表明我们的方法提供了良好的检索性能，同时与 JPEG 压缩域算法相比，速度提高了 30 倍以上，与在线图像检索的常见像素域技术相比，速度提高了 150 倍以上。
Visual information on the web, in particular in form of images, is increasing at a rapid rate. Consequently, efficient and effective techniques to retrieve visual information are sought after, especially since users rarely annotate images. In this paper, we present a very fast method for content-based image retrieval of JPEG compressed images. Our method works directly in the compressed domain of JPEG and is based solely on information available in the image header. We make use of the fact that the Huffman tables that JPEG uses for entropy coding can be optimised to maximise compression. Since this process adapts the Huffman tables to the image content, we utilise the tables directly, in particular the prefix code lengths of AC luminance and chrominance table entries, as image features, and employ the L1 distance between the code length vectors as similarity measure. We evaluate our method on benchmark databases of varying sizes up to in excess of 1 million images, and show that our approach provides good retrieval performance, while providing a more than 30-fold speedup compared to JPEG compressed domain algorithms and more than 150-fold compared to common pixel domain techniques for online image retrieval.