Content Based Multimedia Information Retrieval to Support Digital Libraries
This work addresses the challenge of inconsistent retrieval systems for digital libraries, offering a unified approach, though it appears incremental as it builds on existing research in content-based retrieval.
The paper tackles the problem of retrieving multimedia objects like images and video clips based on their inherent characteristics, such as color, shapes, textures, and spatial relationships, by proposing an integrated model that allows uniform retrieval across both media types within the same framework.
Content-based multimedia information retrieval is an interesting research area since it allows retrieval based on inherent characteristic of multimedia objects. For example retrieval based on visual characteristics such as colour, shapes or textures of objects in images or retrieval based on spatial relationships among objects in the media (images or video clips). This paper reviews some work done in image and video retrieval and then proposes an integrated model that can handle images and video clips uniformly. Using this model retrieval on images or video clips can be done based on the same framework.