An Efficient Face Image Retrieval through DCT Features Aamer. S. S. Mohamed, Ying Weng, Jianmin Jiang and Stan Ipson School of Informatics, University of Bradford BD7 1DP, UK { A.S.S.mohamed, Y.Weng, J.Jiang1, S.S.Ipson}@Bradford.ac.uk ABSTRACT This paper proposes a new simple method of DCT feature extraction that utilize to accelerate the speed and decrease storage needed in image retrieving process by the aim of direct content access and extraction from JPEG compressed domain. Our method extracts the average of some DCT block coefficients. This method needs only a vector of six coefficients per block over the whole image blocks In our retrieval system, for simplicity, an image of both query and database are normalized and resized from the original database based on the cantered position of the eyes, the normalized image equally divided into non overlapping 8X8 block pixel Therefore, each of which are associated with a feature vector 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 that our approach is easy to identify main objects and reduce the influence of background in the image, and thus improve the performance of image retrieval. KEY WORDS Content-based image retrieval, JPEG, Discrete cosine transforms, Feature extraction. 1. Introduction Content based image retrieval (CBIR) is a hot topic research in the last decade. A number of image feature based on color, texture, and shape attributes in various domains have been reported in the literature [1, 2]. Recent research is started to develop image analysis and content feature extraction directly from compressed domain [5]. CBIR system can be classified as two phases: indexing and searching. In the indexing phase, each image of the database is represented by a set of attribute features color, texture and shape. In searching phase, when the user selects a query image, a query vector feature is computed. Using similarity distance measure well know Euclidian distance, the query vector compared to the feature vectors in the feature database and retrieve to the user the images that most close or similar to the query image. To provide a fast feature extraction for compressed domain, therefore, a new wave of research efforts is direct access to feature extraction in compressed domain [3, 4]. All existing research on compressed domain is limited to DCT domain. The logic behind is that DCT is a good approximation of principal component extraction, which helps to process and highlight the signal frequency features. In this paper we propose a simple method for face image retrieval based on DCT coefficient, we extract the average of some DCT coefficient features per block over the entire of the whole image. Then these features for each image blocks are concatenated to construct a feature vector. The rest of the paper is organized as follows: in section ii a brief content based image retrieval. In section iii gives brief descriptions of DCT based block transform. In section iv how to extract features vectors from DCT. In section v presents how to measure the similarity distance and in section vi experimental results. Section vii gives the conclusion 2. Content Based Image Retrieval Content-based image retrieval systems have been dealt with the issue of automatic indexing and retrieval of images. The general image retrieval system is shown in Figure 1. It consists of three main modules such as input module, query module, and retrieval module [6]. Fig.1. Block diagram of image retrieval system In the input module, the feature vector is extracted from input image. It is then stored along with its input image in the image database. On the other hand, when a query