Hybdrid Content Based Image Retrieval combining multi-objective interactive genetic algorithm and SVM
Résumé
The amount of images contained in repositories or available on Internet has exploded over the last years. In order to retrieve efficiently one or several images in a database, the development of Content-Based Image Retrieval (CBIR) systems has become an intensively active research area. However, most proposed systems are keyword-based and few imply the end-user during the search (through relevance feedback). Visual low-level descriptors are then substituted to keywords but there is a gap between visual description and user expectations. We propose a new framework which combines a multi-objective interactive genetic algorithm, allowing a trade-off between image features and user evaluations, and a support vector machine to learn the user relevance feedback. We test our system on SIMPLIcity database, commonly used in the literature to evaluate CBIR systems using a genetic algorithm, and it outperforms the recent frameworks.
Mots clés
- Support vector machines
- Internet
- content-based retrieval
- feature extraction
- interactive systems
- relevance feedback
- visual databases
- CBIR systems
- SIMPLIcity database
- SVM
- hybrid content-based image retrieval
- Vectors
- Training
- image database
- Sociology
- Image retrieval
- Genetic algorithms
- visual low-level descriptors
- visual description
- user relevance feedback
- user expectations
- user evaluation
- support vector machine
- multiobjective interactive genetic algorithm
- keyword-based system
- image repository
- image features
