| Grant number: | 17/02091-4 |
| Support type: | Scholarships in Brazil - Master |
| Effective date (Start): | May 01, 2017 |
| Effective date (End): | March 31, 2019 |
| Field of knowledge: | Physical Sciences and Mathematics - Computer Science |
| Cooperation agreement: | Coordination of Improvement of Higher Education Personnel (CAPES) |
| Principal Investigator: | Daniel Carlos Guimarães Pedronette |
| Grantee: | Lucas Pascotti Valem |
| Home Institution: | Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil |
| Associated research grant: | 13/08645-0 - Re-Ranking and rank aggregation approaches for image retrieval tasks, AP.JP |
Abstract The evolution of the mobile devices and the consequent facilities in the processes of acquisition and sharing of visual content have caused a great growth in the collections of images. In this scenario, it becomes imperative to develop automatic methods that allow indexing, analyzing and searching in such content. Content-Based Image Retrieval (CBIR) are a promising solution. However, assessing the similarity between the visual content of images presents several challenges. Unsupervised Learning have firmed as a solution to improve the effectiveness of retrieval systems without requiring user intervention. As several methods have been developed using distinct and complementary approaches, new research challenges emerge regarding the combination of these methods in order to increase the gains. This research project intends to investigate and propose strategies for selection and aggregation the unsupervised learning methods. (AU) | |