University of Surrey

Test tubes in the lab Research in the ATI Dance Research

An efficient image retrieval through DC feature extraction

Irianto, YS, Jiang, J and Ipson, SS (2006) An efficient image retrieval through DC feature extraction Proceedings of the Fourth IASTED International Conference on Circuits, Signals, and Systems, CSS 2006. pp. 17-20.

Full text not available from this repository.


We propose a new simple method of DC feature extraction that enables to speed up and decrease storage needed in image retrieving process by aim of partial Joint Photographic Experts Group (JPEG) compressed images algorithm. Our feature extraction is carried out directly from JPEG compressed images. We extract one component of DCT coefficients which is DC component only. By applying DC feature, we only need 1/64 times that is required to construct indexing keys compared to conventional Euclidean distance method whilst maintaining high precision and recall. We also use a DCT coding category approach to compare our proposed method. After all, even though this method is not revolutionary and perfect yet in improving speed for image indexing, it reduces significantly the cost of image retrieval in real applications, primarily for huge image databases.

Item Type: Article
Divisions : Surrey research (other units)
Authors :
Irianto, YS
Ipson, SS
Date : 1 December 2006
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 12:24
Last Modified : 24 Jan 2020 22:11

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800