随着多媒体技术和因特网的发展,基于内容的图象检索已经成为多媒体处理中的关键技术,而基于压缩域的图象检索由于其低复杂性逐渐形成一个新的研究热点.针对当前网上图像浏览与检索的应用要求,本文提出了一种基于JPEG2000压缩码流的压缩图象快速检索方法.该方法直接从JPEG2000压缩码流包头中抽取码块零位平面数,码块编码通道数及码块编码长度信息,并进而构造特征矢量用于图象检索.初步实验结果验证了该方法的有效性和快速性.
Abstract
Multimedia and INTERNET is increasingly developing in recent years. It is crucial to develop indexing techniques for searching images and video based on their content. Dne to the lower computational complexity. compressed domain indexing lech-piques are becoming popular. In this paper, an efficient compressed image indexing scheme based on JPEG2000 framework is proposed. The target application is the access and interaction with huge amount of visual data on intemet. Here, the information on the number of zero bit-planes in code-blocks, number of coding passes in code-blocks and length of the data from code-blocks is directly extracted from the packet header of a JPEG2000 compressed image without decompressing the bitstream. A featuer vector is built based on the three-part information and is used as the image index. Preliminary experimental results show that the proposed scheme is efficient and effective.
关键词
JPEG2000 /
基于内容 /
图象检索 /
网上检索
{{custom_keyword}} /
Key words
JPEG2000 /
content-based /
image indexing /
Internet retrieval
{{custom_keyword}} /
中图分类号：
TP391
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Smeulders A W M,Worring M,Santini S,et al.Content-based image retrieval at the end of the early years[J].IEEE transactions on pattern analysis and machine intelligence,2000,22(12):1349-1379.
[2] Mandal M K,Idris F,Panchanathan S.A critical evaluation of image and video indexing techniques in the compressed domain[J].Image and Vision Computing,1999,17:513-529.
[3] Christopoulos C,Skodras A,Ebrahimi T.The JPEG2000 still image coding system:an overview[J].IEEE Transactions on Consumer Electronics,2000,46(4):1103-1127.
[4] ISO/IEC 15444-1,JPEG 2000 Part-1 standard[S].2000.
[5] 魏海,沈兰荪.小波变换域内基于方向梯度相角直方图的图像检索算法[J].电路与系统学报,2001,6(2):20-24.
[6] 魏海,沈兰荪.反对称双正交小波应用于多尺度边缘提取的研究[J].电子学报,2002,30(3):313-316.
[7] Nicu Sebe,M S Lew.Wavelet based texture classification[A].Proc.of the 15th International Conference on Pattern Recognition[C].Spain:Barcelona,2000.947-950.
[8] Flickner M,Sawhney H.Query by image and video content:The QBIC system[J].Computer,1995,28:23-32.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金 (No.60172045); 北京市自然科学基金 (No.4002002)
{{custom_fund}}
PDF(817 KB)
