Abstract
A fully automatic system for organizing and browsing digital image collections is presented. The system is based on detecting and classifying the people present in the Images according to their similarity with the target person. Face detection, face recognition and additional methods are used in order to obtain a fully automatic system. In order to increase the robustness of the system to different factors that influence the accuracy of the face recognition systems, more than one type of features were extracted from the face region and used in the recognition stage and also additional information obtained from different regions than the face were extracted and used in classification.
| Original language | English (Ireland) |
|---|---|
| Title of host publication | Hybrid techniques for automatic person retrieval from image collections |
| Number of pages | 6 |
| Publication status | Published - 1 Jun 2006 |
Authors (Note for portal: view the doc link for the full list of authors)
- Authors
- Corcoran, P,Costache, GN,Mulryan, R,Cernat, M,Nicolaide, A,Margineanu I