Image retrieval in the unstructured data management system AUDR

Abstract

The explosive growth of image data leads to severe challenges to the traditional image retrieval methods. In order to manage massive images more accurate and efficient, this paper firstly proposes a scalable architecture for image retrieval based on a uniform data model and makes this function a sub-engine of AUDR, an advanced unstructured data management system, which can simultaneously manage several kinds of unstructured data including image, video, audio and text. The paper then proposes a new image retrieval algorithm, which incorporates rich visual features and two text models for multi-modal retrieval. Experiments on both ImageNet dataset and ImageCLEF medical dataset show that our proposed architecture and the new retrieval algorithm are appropriate for efficient management of massive image.