Abstract:

With the rapid growing of multimedia technology, more and more multimedia content are disseminated in the network or stored in the database.  Image data is one of the multimedia types to be seen or accessed for the users in the Internet or from the database.  Searching the related images by querying image’s content is helpful to the management and the usage of image database.    Therefore, the research of image indexing technique is an important topic.  In this paper, we propose an efficient content-based image retrieval (CBIR) system.  The user can select the region of interest (ROI) and the system will search all the images in the database to find the all related regions among the database.  Basically, the proposed method is a DCT coefficients based technique which extracts the content features by using some discrete cosine transform (DCT) coefficients.  In addition, our method also uses entropy to classify images in the database so that it can reduce the searching space to decrease the processing time. According to our experiment results, the system has highly efficiency in terms of robustness, precision and processing speed.

Keywords: Content-Based Image Retrieval (CBIR), Entropy, Region of Interest (ROI), Image Database

Author Biography:

Yung-Gi, Wu received his BS in information and computer engineering from Chung Yuan Christian University, Chung-Li, Taiwan, in 1992, and his MS and PhD in electrical engineering from the National Cheng Kung University, Tainan, Taiwan, in 1994 and 2000, respectively. From 1994 to1996, he was a Reserve Officers’ Training Corps (ROTC) officer in the army.  He was an assistant professor in the Department of Computer Science and Information Engineering and the Institute of Applied Information, Leader University, Tainan, Taiwan from 2000 to 2003.  He is current an associate professor since December, 2003.  His research interests include image database indexing, image processing, and nonlinear optimization.

 

BibTex:

@ARTICLE{P1150636004,

AUTHOR = {Wu  Yung-Gi},

TITLE = {Region of Interest Image Indexing System by DCT and Entropy},

JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing},

}

(Full Paper 1.25 MB)