Content-Based Image Retrieval: on the Way to Object Features

Abstract : Content-based systems retrieve images based on low-level features (color,texture) while the user usually seeks some objects from real world. As segmentation is never accurate, such systems do not allow the use of powerful feature during retrieval (shape, structure). We propose a new system that relies on a hierarchy of segmentations, in order to handle some artifacts. Besides, it allows using some object-related features for indexing (shape, structure). We also present some result on a 600 images database from Corel.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01613494
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Monday, October 9, 2017 - 4:35:59 PM
Last modification on : Monday, December 10, 2018 - 5:47:40 PM

Identifiers

  • HAL Id : hal-01613494, version 1

Citation

Nicolas Zlatoff, Guillaume Ryder, Bruno Tellez, Atilla Baskurt. Content-Based Image Retrieval: on the Way to Object Features. International Conference on Pattern Recognition, ICPR 2006, Aug 2006, Hong Kong, China. ⟨hal-01613494⟩

Share

Metrics

Record views

61