Int. J. of Dynamical Systems and Differential Equations   »   2018 Vol.8, No.1/2

 

 

Title: Content frequency and shape features based on CBIR: application to colour images

 

Authors: Chawki Youness; El Asnaoui Khalid; Ouanan Mohammed; Aksasse Brahim

 

Addresses:
Faculty of Science and Techniques, M2I Laboratory, ASIA Team, Department of Computer Sciences, Moulay Ismail University, BP 509 Boutalamine, Errachidia, Morocco
Faculty of Science and Techniques, M2I Laboratory, ASIA Team, Department of Computer Sciences, Moulay Ismail University, BP 509 Boutalamine, Errachidia, Morocco
Faculty of Science and Techniques, M2I Laboratory, ASIA Team, Department of Computer Sciences, Moulay Ismail University, BP 509 Boutalamine, Errachidia, Morocco
Faculty of Science and Techniques, M2I Laboratory, ASIA Team, Department of Computer Sciences, Moulay Ismail University, BP 509 Boutalamine, Errachidia, Morocco

 

Abstract: Due to the diversity of the image content, we propose in this study a new technique for content-based image retrieval to characterise the image. In this scenario, all images are characterised by their frequency content and their shape information. Indeed, using the high-resolution spectral analysis methods, especially the 2-D estimation of signal parameters via rotational invariance techniques, we extract from the image its content frequency and with the angular radial transform its shape information to construct a new vector descriptor. The experimental results applied to the Coil_100 database show the effectiveness and the robustness of our approach compared with the method based on the shame information only, and the precision average can be reached as 74.49%.

 

Keywords: ART; CBIR; 2-D ESPRIT; frequency content; high resolution; shape feature; spectral analysis.

 

DOI: 10.1504/IJDSDE.2018.10009168

 

Int. J. of Dynamical Systems and Differential Equations, 2018 Vol.8, No.1/2, pp.123 - 135

 

Date of acceptance: 02 Aug 2017
Available online: 30 Nov 2017

 

 

Editors Full text accessAccess for SubscribersPurchase this articleComment on this article