Gabor filter-based texture features to archaeological ceramic materials characterization

Authors:
Mohamed Abadi;Majdi Khoudeir;Sylvie Marchand
Affiliations:
XLIM-SIC Department, UMR CNRS 6172, Chasseneuil-Futuroscope, France;XLIM-SIC Department, UMR CNRS 6172, Chasseneuil-Futuroscope, France;Institut français d'archéologie orientale, Cairo, Egypt
Venue:
ICISP'12 Proceedings of the 5th international conference on Image and Signal Processing
Year:
2012

Citing 8
Cited 0

Using Discriminant Eigenfeatures for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition: The Problem of Compensating for Changes in Illumination Direction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Filtering methods for texture discrimination

Pattern Recognition Letters
Face Verification with Gabor Representation and Support Vector Machines

AMS '07 Proceedings of the First Asia International Conference on Modelling & Simulation
A Comparative Study for Texture Classification Techniques on Wood Species Recognition Problem

ICNC '09 Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 05
A multiscale representation including opponent color features for texture recognition

IEEE Transactions on Image Processing
Optimal Gabor filters for texture segmentation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a self-learning system for automatic texture characterization and classification on ceramic pastes or fabrics and surfaces. The system uses Gabor filter as pre-processing methods with feature extraction possibilities. On these features it applies a linear discriminant analysis (LDA) and k-nearest neighbor classifiers (k-NN) with its best parameters. Experimental results of the recognition ceramic materials, deals on the field and in the laboratory, for different ceramic pastes and surfaces show a good accuracy and applicability of the process on this type of data.