Content-based Image Retrieval: Feature Extraction Techniques and Applications

The emergence of multimedia technology and the rapidly expanding image collections on the Internet have attracted significant research efforts in providing tools for effective retrieval and management of visual data. The need to find a desired image from a large collection is shared by many professional groups, including journalists, design engineers and art historians. Difficulties faced by text-based image retrieval brought the researchers to develop new solutions to represent and index visual information. This new trend of image retrieval was based on properties that are inherent in the images themselves and was called Content-Based Image Retrieval. "Content-based" means that the search will analyze the actual contents of the image. Image content descriptors may be visual features such as color, texture, shape or spatial relationships. The research in CBIR field is motivated by the large amount of potential applications that the new technologies offer.