Skip to Main content Skip to Navigation

An hybrid method for fine-grained content based image retrieval

Abstract : Given the ever growing amount of visual content available on the Internet, the need for systems able to search through this content has grown. Content based image retrieval systems have been developed to address this need. But with the growing size of the databases, new challenges arise. In this thesis, the fine grained classification problem is studied in particular. It is first shown that existing techniques, and in particular the support vector machines which are one of the best image classification technique, have some difficulties in solving this problem. They often lack of exploration in their process. Then, evolutionary algorithms are considered to solve the problem, for their balance between exploration and exploitation. But their performances are not good enough either. Finally, an hybrid system combining an evolutionary algorithm and a support vector machine is proposed. This system uses the evolutionary algorithm to iteratively feed the support vector machine with training samples. The experiments conducted on Caltech-256, a state of the art database containing around 30000 images, show very encouraging results
Document type :
Complete list of metadatas

Cited literature [92 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Tuesday, February 28, 2017 - 10:36:30 AM
Last modification on : Monday, October 12, 2020 - 10:30:41 AM
Long-term archiving on: : Monday, May 29, 2017 - 1:15:42 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01478403, version 1



Romaric Pighetti. An hybrid method for fine-grained content based image retrieval. Other [cs.OH]. Université Côte d'Azur, 2016. English. ⟨NNT : 2016AZUR4085⟩. ⟨tel-01478403⟩



Record views


Files downloads