Improving Texture Categorization with Biologically Inspired Filtering

Abstract : Within the domain of texture classification, a lot of effort has been spent on local descriptors, leading to many powerful algorithms. However, preprocessing techniques have received much less attention despite their important potential for improving the overall classification performance. We address this question by proposing a novel, simple, yet very powerful biologically-inspired filtering (BF) which simulates the performance of human retina. In the proposed approach, given a texture image, after applying a difference of Gaussian (DoG) filter to detect the edges, we first split the filtered image into two maps alongside the sides of its edges. The feature extraction step is then carried out on the two maps instead of the input image. Our algorithm has several advantages such as simplicity, robustness to illumination and noise, and discriminative power. Experimental results on three large texture databases show that with an extremely low computational cost, the proposed method improves significantly the performance of many texture classification systems, notably in noisy environments.
Type de document :
Article dans une revue
Image and Vision Computing, Elsevier, 2014, 6-7, 3, pp.424-436
Liste complète des métadonnées
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : dimanche 10 septembre 2017 - 15:09:53
Dernière modification le : jeudi 3 mai 2018 - 15:18:05


  • HAL Id : hal-01584903, version 1


Ngoc-Son Vu, Thanh Phuong Nguyen, Christophe Garcia. Improving Texture Categorization with Biologically Inspired Filtering. Image and Vision Computing, Elsevier, 2014, 6-7, 3, pp.424-436. 〈hal-01584903〉



Consultations de la notice