Indexing Of Three Dimensions Objects Using GIST, Zernike & PCA Descriptors

Driss Naji
Fakir Mohamed Fakir (Faculty of Sciences and Technics)
O. Bencharef
B. Bouikhalene
A. Razouk

IAES International Journal of Artificial Intelligence (IJ-AI)
Vol 2, No 1: March 2013

In this paper, we present a new approach to object to recognition based on the combination of Zernike moments, descriptors Gist and PCA pair wise applied to color images. The recognition of objects are based on two approaches of classification the first use neural networks (NN) for learning stage and gratitude as well to the Support Vector Machines (SVM). The experimental results showed that the recognition by SVM is better than NN. We illustrate the proposed method on color images, including objects from the database COIL-100.DOI: http://dx.doi.org/10.11591/ij-ai.v2i1.825