Skip to Main content Skip to Navigation
New interface
Conference papers

Image Retrieval Using Local Characterization

Cordelia Schmid 1 Roger Mohr 1 
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : The paper presents a general method to retrieve images from large databases using images as queries. The method is based on local characteristics which are robust to the group of similarity transformations in the image. Images can be retrieved even if they are translated, rotated or scaled. Due to the locality of the characterization, images can be retrieved even if only a small part of the image is given as well as in the presence of occlusions. A voting algorithm, following the idea of a Hough transform, and semi local constraints allow us to develop a new method which is robust to noise, to scene clutter and small perspective deformations. Experiments show an efficient recognition for different types of images. The approach has been validated on an image database containing 1020 images, some of them being very similar by structure, texture or shape.
Document type :
Conference papers
Complete list of metadata
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Tuesday, May 31, 2011 - 12:07:39 PM
Last modification on : Friday, February 4, 2022 - 3:24:13 AM
Long-term archiving on: : Friday, December 2, 2016 - 5:49:32 PM


Publisher files allowed on an open archive




Cordelia Schmid, Roger Mohr. Image Retrieval Using Local Characterization. International Conference on Image Processing (ICIP '96)), Sep 1996, Lausanne, Switzerland. pp.781--784, ⟨10.1109/ICIP.1996.561020⟩. ⟨inria-00548367⟩



Record views


Files downloads