Year: 2012
Type: dissertation
Abstract: [ANGLÈS] This project aims to implement a prototype of large-scale image retrieval with the Fisher Kernel Framework. The project report first introduces the problem of large-scale image search. The Fisher Kernel Framework (FKF) is then explained in more detail, followed by the comparison between different solutions and analysis. In the implementation, the experimental setup is first described together with the process step-by-step. Finally, an image retrieval software with a user interface tests the framework performance on several databases in terms of different evaluation measures.
Author: Santiago Herrero Bajo
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W137680956