Skip to Main content Skip to Navigation
Book sections

Numerical training for the information research in medical imagery : Modeling of the Gabor filters

Sahbi Sidhom 1 Noureddine Bourkache 2 Mourad Laghrouche 3
1 KIWI - Knowledge Information and Web Intelligence
LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
2 Laboratoire Lampa
LAMPA - Laboratoire d'Analyse & Modélisation des Phénomènes Aléatoires [Tizi-Ouzou]
Abstract : We propose, in this paper, a method of image indexing and research by exploiting the digital component of the images. Our method is founded on the representation of the image digital component by a vector of characteristics its own for the indexed image. This vector will be called: numerical signature of the image. With this intention, we exploited the texture of the image by using the Gabor’s wavelets. In this work, each image of the training base is indexed and represented by its characteristics (texture). This representation, which is carried out in offline, is characterized by the saving, in a data base, of all the signatures of the indexed images. What enables us, in online, to carry out a numerical search for similarity compared to a request image. This same request image will be indexed in online with the same algorithm used in offline. In order to evaluate the performances we tested our application on a training images basis containing 320 mammography. The results obtained show well that the representation of the digital component of the images proves to be significant as regards search for information in imagery.
Complete list of metadatas
Contributor : Sahbi Sidhom <>
Submitted on : Saturday, January 24, 2015 - 7:32:21 PM
Last modification on : Tuesday, December 18, 2018 - 4:40:21 PM


  • HAL Id : hal-01109145, version 1



Sahbi Sidhom, Noureddine Bourkache, Mourad Laghrouche. Numerical training for the information research in medical imagery : Modeling of the Gabor filters. ISKO International. Knowledge organization in the 21st century: between historical patterns and future prospects, Ergon, pp.8, 2014, 9783956500404. ⟨hal-01109145⟩



Record views