With the availability of internet technology and the low-cost of digital image sensor, enormous amount of image databases have been created in different kind of applications. These image databases increase the demand to develop efficient image retrieval search methods that meet user requirements. Great attention and efforts have been devoted to improve content-based image retrieval method with a particular focus on reducing the semantic gap between low-level features and human visual perceptions. Due to the increasing research in this field, this paper surveys, analyses and compares the current state-of-the-art methodologies over the last six years in the CBIR field. This paper also provides an overview of CBIR framework, recent low-level feature extraction methods, machine learning algorithms, similarity measures, and a performance evaluation to inspire further research efforts.

Large number of image datasets have been generated with diverse functionality and applications. This is because of the development in communication technologies and affordable image acquisition devices. However, the generated image datasets require an efficient search engine to retrieve images that meet the needs of end-user. Content-Based Image Retrieval (CBIR) is an automatic mechanism to retrieve images from relevant class according to their visual content. In this paper, local and global features are combined to provide a powerful image descriptor. CBIR performance is measured through two major key factors which are: accuracy and retrieval time. The first one is related to the amount of retrieved images from the same semantic class while the latter is related to the speed of the search. There is a tradeoff between these two factors. In this regard, this paper proposes CBIR algorithm based on feature fusion and support vector machine (SVM). The feature are texture, shape, and color features. The statistical moments, mean and standard deviation are calculated after transforming the RGB channels to moments' domain through the use of SKTP to construct the color descriptor. Canny Edge Detection and LBP are utilized to construct edge and texture descriptors, respectively. WANG dataset is used to assess the performance of the proposed algorithms. The proposed algorithm focused on achieving an interesting accuracy level (90.15 %) through the use of SVM classifier. Thus, the proposed algorithm achieved its goal and outperformed existing algorithms.