摘要
针对DCT在图像编码中的重要地位,进行了基于加权DCT系数的图像检索算法研究。以MPEG-7中的颜色布局描述符为图像特征,根据DCT系数的能量分布特征,选取适当数量的DCT系数,并对所选取DCT系数赋以不同的权重得到新的颜色特征,采用欧氏距离作为相似度量直接在DCT域内对彩色图像进行检索。并在此基础上研究了DCT系数权重的选择与图像检索性能之间的关系,最后对检索结果进行了比较详细的分析。结果表明,根据具体情况对DCT系数选择适当的权重可以得到比较满意的检索结果。
According to the important position of DCT in image coding, the research of image retrieval performance based on weigilted DCT coefficient is advanced. The research based on DCT coefficient energy distribution character takes color descriptors of MPEG -7 as the color image teature, acquires new image features through giving different weights to the different elected DCT coefficients, and uses Euclidean distance as the similar distance measurement to retrieve color images in DCT. Then the relationship between ttle choice of weight and retrieval performance is studied in experiments, and moreover the retrieval conclusion is analyzed very closely. The result shows it can acquire relatively satisfactory outcome if selecting right weights of the elected DCT coefficients based on a concrete condition.
出处
《网络新媒体技术》
2016年第3期22-26,共5页
Network New Media Technology
基金
陕西省科技厅项目(2014JQ2-6031)
陕西省教育厅项目(15JK1827)
延安市科学技术研究发展计划项目(2014KG-02)
延安大学青年基金项目(YDQ2014-37)支持
作者简介
张水利,(1974.8-),女,讲师,主要研究方向:图像处理。