Title :
Research on JPEG Image Retrieval
Author :
Shan, Zhao ; Liu, Yan-Xia
Author_Institution :
Sch. of Comput. Sci. & Technol., Henan Polytech. Univ., Jiaozuo, China
Abstract :
A novel image retrieval of JPEG image is proposed combing the statistical distribution with spatial information of the DCT coefficients. Firstly, according to the distribution of DC coefficients, a robust DC feature is presented. Meantime, several AC coefficients are chosen to extracted AC feature. Furthermore, the effect of the spatial information of the AC coefficients on retrieval result is considered, a weight is introduced to improve the scheme. The experiment results show that the proposed method has a good performance both in retrieval efficiency and effectiveness.
Keywords :
content-based retrieval; discrete cosine transforms; feature extraction; image retrieval; DCT coefficients; JPEG image retrieval; content-based retrieval; discrete cosine transform; statistical distribution; Computer science; Data mining; Discrete cosine transforms; Discrete transforms; Entropy; Feature extraction; Image coding; Image retrieval; Information retrieval; Transform coding;
Conference_Titel :
Wireless Communications, Networking and Mobile Computing, 2009. WiCom '09. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-3692-7
Electronic_ISBN :
978-1-4244-3693-4
DOI :
10.1109/WICOM.2009.5303112
