Abstract
Due to the recent technology development, the multimedia complexity is noticeably increased and new research areas are opened relying on similar multimedia content retrieval. Content-based image retrieval (CBIR) systems are used for the retrieval of images related to the Query Image (QI) from huge databases. The CBIR systems available today have confined efficiency as they extract only limited feature sets. This paper demonstrates the extraction of vast robust and important features from the images database and the storage of these features in the repository in the form of feature vectors. The feature repository contains color signature, the shape features and texture features. Here, features are extracted from specific QI. Accordingly, an innovative similarity evaluation with a metaheuristic algorithm (genetic algorithm with simulating annealing) has been attained between the QI features and those belonging to the database images. For an image entered as QI from a database, the distance metrics are used to search the related images, which is the main idea of CBIR. The proposed CBIR techniques are described and constructed based on RGB color with neutrosophic clustering algorithm and Canny edge method to extract shape features, YCbCr color with discrete wavelet transform and Canny edge histogram to extract color features, and gray-level co-occurrence matrix to extract texture features. The combination of these methods increases the image retrieval framework performance for content-based retrieval. Furthermore, the results' precision-recall value is calculated to evaluate the system's efficiency. The CBIR system proposed demonstrates better precision and recall values compared to other state-of-the-art CBIR systems.