Multi-Modal Interactive Approach to ImageCLEF 2007 Photographic and Medical Retrieval Tasks by CINDI
Md Mahmudur Rahman, Bipin C. Desai, Prabir Bhattacharya · 2007
This paper presents the contribution of CINDI group to the ImageCLEF 2007 ad-hoc retrieval tasks. We experiment with multi-modal (e.g., image and text) in-teraction and fusion approaches based on relevance feedback information for image retrieval tasks of photographic and medical image collections. For a text-based image search, keywords from the annotated files are extracted and indexed by employing the vector space model of information retrieval. For a content-based image search, various global, semi-global, region-specific and visual concept-based features are extracted at different levels of image abstraction. Based on relevance feedback information, multi-ple textual and visual query refinements are performed and user’s perceived semantics are propagated from one modality to another with query expansion. The feedback information also dynamically adjusts intra and inter-modality weights in linear com-bination of similarity matching functions. Finally, the top ranked images are obtained by performing both sequential and simultaneous retrieval approaches. The analysis of results of different runs are reported in this paper.