Abstract | ||
---|---|---|
In this work, we take into account the non gaussian properties of textures and we propose a new approach for their characterization based on bidimensional adaptive modelisation using higher order statistics. The 2D-OLRIV (Bidimensionnal Overdetermined Lattice Recursive Instrumental Variable) algorithm allows accurate texture model estimation. Sets of 2D-AR coefficients obtained from the 2D reflection coefficients of the lattice model are used to characterize the texture model. This algorithm has the advantage of yielding non biased estimates of the 2D-AR model even when the texture image is disturbed by gaussian noise. A multilayer neural network deals with these coefficients in order to classify different textures. In order to evaluate the performance of this approach, classification sensitivity is evaluated on a set of eight different textures. This characterization approach gives very promising results. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/ICASSP.1998.678086 | PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6 |
Keywords | Field | DocType |
ar model,adaptive signal processing,performance,cumulant,lattices,lattice model,adaptive filters,backpropagation,adaptive filter,gaussian noise,image classification,image texture,neural networks,backpropagation algorithm,reflection coefficient,instrumental variable | Overdetermined system,Mathematical optimization,Pattern recognition,Image texture,Computer science,Higher-order statistics,Adaptive filter,Artificial intelligence,Adaptive algorithm,Contextual image classification,Artificial neural network,Gaussian noise | Conference |
ISSN | Citations | PageRank |
1520-6149 | 0 | 0.34 |
References | Authors | |
7 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
M. Sayadi | 1 | 9 | 1.67 |
Véronique Buzenac-Settineri | 2 | 0 | 0.34 |
Mohamed Najim | 3 | 149 | 32.29 |