MDCBIR-MF: multimedia data for content-based image retrieval by using multiple features

Abstract

Due to recent development in technology, the complexity of multimedia is significantly increased and the retrieval of similar multimedia content is an open research problem. In the service of multimedia service, the requirement of Multimedia Indexing Technology is increasing to retrieve and search for interesting data from huge Internet. Since the traditional retrieval method, which is using textual index, has limitation to handle the multimedia data in current Internet, alternatively, the more efficient representation method is needed. Content-Based Image Retrieval (CBIR) is a process that provides a framework for image search and low-level visual features are commonly used to retrieve the images from the image database. The basic requirement in any image retrieval process is to sort the images with a close similarity in term of visual appearance. The color, shape, and texture are the examples of low-level image features. The feature combination that is also known as feature fusion is applied in CBIR to increase the performance, a single feature is not robust to the transformations that are in the image datasets. This paper represents a new Content-Based Image Retrieval (CBIR) technique to fuse the color and texture features to extract local features as our feature vector. The features are created for each image and stored as a feature vector in the database. The proposed research is divided into three phases that feature extraction, similarities match, and performance evaluation. Color Moments (CM) are used for Color features and extract the Texture features, used Gabor Wavelet and Discrete Wavelet transform. To enhance the power of feature vector representation, Color and Edge Directivity Descriptor (CEDD) is also included in the feature vector. We selected this combination, as these features are reported intuitive, compact and robust for image representation. We evaluated the performance of our proposed research by using the Corel, Corel-1500, and Ground Truth (GT) images dataset. The average precision and recall measures are used to evaluate the performance of the proposed research. The proposed approach is efficient in term of feature extraction and the efficiency and effectiveness of the proposed research outperform the existing research in term of average precision and recall values.