• Aucun résultat trouvé

Shape-based image retrieval using a new descriptor based on the Radon and wavelet transforms

N/A
N/A
Protected

Academic year: 2021

Partager "Shape-based image retrieval using a new descriptor based on the Radon and wavelet transforms"

Copied!
1
0
0

Texte intégral

(1)

20th International Conference on Pattern Recognition (ICPR) 2010

Shape-based image retrieval using a new descriptor based on the Radon and wavelet

transforms

N. Nacereddine, S. Tabbone, D. Ziou, L. Hamami

Abstract : In this paper, the Radon transform is used to design a new descriptor called Phi-signature invariant to usual geometric transformations. Experiments show the effectiveness of the multilevel representation of the descriptor built from Phi-signature and R-signature.

Keywords : radon transform, Phi-signature; R-signature, Wavelet transform

Centre de Recherche en Technologies Industrielles - CRTI - www.crti.dz

Powered by TCPDF (www.tcpdf.org)

Références

Documents relatifs

In this paper, such a system is proposed for weld radiograms in radiographic testing, with the aim of searching from the overall image database, interactively with the

In fact, the best solution found by the GA, here called H-GA, uses only 31% of the dimensions from the canonical version of the descriptor and still achieves a similar performance.

Symbol descriptor based on shape context and vector model of information retrieval.. Thi Oanh Nguyen, Salvatore Tabbone, Oriol

This paper proposes novel image patch descriptors based on anisotropic half Gaussian derivative kernel (AHGDK) and anisotropic half exponential deriva- tive kernel (AHEDK).

The obtained correspondences are used to map chroma information from the reference to the target image, pro- ducing an initial colorization result.. Finally, a regularization

Therefore, in order to use detected line segments to extract LBTD features, some transformations are needed (Fig.. LICENSE PLATE LOCALIZATION SYSTEM In this section, we describe

Our procedure required two training sets: a set A containing face images that is used for the negative examples during the one-shot learning, and a second set B of matching

Robustness means the algorithm always generates the same (or similar) hash values for similar image contents.. Discrimi- nation means different image inputs must result in