Download presentation
Presentation is loading. Please wait.
Published byAmber Foster Modified over 9 years ago
1
Text- and Content-based Approaches to Image Retrieval for the ImageCLEF 2009 Medical Retrieval Track Matthew Simpson, Md Mahmudur Rahman, Dina Demner-Fushman, Sameer Antani, George R. Thoma Lister Hill National Center for Biomedical Communications, National Library of Medicine, NIH, Bethesda, MD, USA CLEF 2009
2
Retrieval tasks and approaches ITI project long term goal –Find a way to combine image and text features so that the whole is greater than the sum of its parts Ad-hoc image retrieval –Text-based –Image content-based –Automatic mixed –Relevance feedback mixed Case-based document retrieval –Text-based
3
Text-based approach Indexing: –Create image documents for ad-hoc image retrieval –Create surrogate documents for case-based retrieval –Index using Essie term normalization using the SPECIALIST Lexicon query expansion based on UMLS synonymy term weighting based on location in the document Phrase-based search
4
Text documents Image document –Title and caption provided by organizers –Mention extracted from paper –MEDLINE citation (abstract +MeSH) –PICO frame of the caption + image modality (structured caption summary) Surrogate document –MEDLINE citation –caption, mention, and structured caption summary of each image contained in the article
5
Text retrieval PICO-based structured query and case representation – 19 Crohn's disease CT – ct c.a.t. cat compu terised axial tomography …. – Crohn's disease crohn disease Regional enteritis eleocolitis Cicatrizing enterocolitis granulomatous enteritis INFLAMMATORY BOWEL DISEASE regional enterocolitis …
6
CBIR - Image feature representation Concepts - color and texture patches from local image regions Low-level global features –Color (Color Layout Descriptor, MPEG-7) –Edge (histogram of local edge distribution and direction) –Texture (grey level co-occurrence matrix) –Average grey level (256-dimensional vector of blocks in image normalized to gray-level 64x64) –Lucene (LIRE)-based Color Edge Direction Descriptor and Fuzzy Color Texture Histogram
7
Image similarity computation Category-specific –Determine image category (training set of 5000 images manually assigned to 32 mutually exclusive categories) –Use category-specific weights in linear similarity matching Relevance feedback –Feature weights updated using images judged relevant
8
Combining text and image Based on text search results, –Compute mean vector of top 5 retrieved images, use as input to category-specific retrieval –Select 3-5 relevant images manually, use as input to category-specific retrieval –Re-rank text retrieval results using visual retrieval scores Provide feedback using all retrieval results, –expand query using image documents –Pad selected relevant images with new retrieval results
9
Relevance Feedback
10
Results visual category- specific RFtext mixed re- ranked case-basedBRFRFRF+QE
11
Image-text search engine
12
Thank you! Questions?
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.