An efficient feature extraction technique based on the histogram of block DCT coefficients

Aamer Mohamed, Fouad Khelifi, Jianmin Jiang, Stanley Ipson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


This paper proposes an efficient content-based image feature extraction technique in the DCT domain using histogram quantization. The features are extracted from DCT block coefficients. These coefficients represent the low frequency content of the input image. This method extracts and constructs a feature vector of histogram quantization from partial DCT coefficient in order to count the number of coefficients having the same DCT coefficient over all image blocks. The database image and query image is equally divided into non overlapping 8X8 block pixel Therefore, each of which are associated with a feature vector of histogram quantization derived directly from discrete cosine transform DCT. Users can select any query as the main theme of the query image. The retrieval images is the relevance between a query image and any database image, the relevance similarity is ranked according to the closest similar measures computed by the Euclidean distance. The experimental results show significant promising results that our approach is easy to identify main objects and try to reduce the influence of background in the image, and thus improve the performance of image classification.
Original languageEnglish
Title of host publicationProceedings of the seventh IASTED international conference on signal processing, pattern recognition, and applications
EditorsB. Zagar, A. Kuijper, H. Sahbi
Place of PublicationAnaheim
PublisherACTA Press
ISBN (Print)9780889868229
Publication statusPublished - 1 Jan 2010
Externally publishedYes
EventThe Seventh IASTED Internal Conference: Signal Processing, Pattern Recognition and Applications SPPRA 2010 - Innsbruck, Austria
Duration: 17 Feb 201019 Feb 2010


ConferenceThe Seventh IASTED Internal Conference
Internet address


Dive into the research topics of 'An efficient feature extraction technique based on the histogram of block DCT coefficients'. Together they form a unique fingerprint.

Cite this