Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis

Hicham Badri
  • Function : Author
  • PersonId : 933343
Hussein Yahia
Khalid Daoudi
  • Function : Author
  • PersonId : 881659

Abstract

A fast and accurate texture recognition system is presented. The new approach consists in extracting locally and globally invariant representations. The locally invariant representation is built on a multi-resolution convolutional net- work with a local pooling operator to improve robustness to local orientation and scale changes. This representation is mapped into a globally invariant descriptor using multifractal analysis. We propose a new multifractal descriptor that cap- tures rich texture information and is mathematically invariant to various complex transformations. In addition, two more techniques are presented to further im- prove the robustness of our system. The first technique consists in combining the generative PCA classifier with multiclass SVMs. The second technique consists of two simple strategies to boost classification results by synthetically augment- ing the training set. Experiments show that the proposed solution outperforms existing methods on three challenging public benchmark datasets, while being computationally efficient.
Fichier principal
Vignette du fichier
eccv2014.pdf (9.36 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01064793 , version 1 (17-09-2014)

Identifiers

  • HAL Id : hal-01064793 , version 1

Cite

Hicham Badri, Hussein Yahia, Khalid Daoudi. Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis. European Conference on Computer Vision, ECCV 2014, Sep 2014, Zürich, Switzerland. ⟨hal-01064793⟩
408 View
544 Download

Share

Gmail Facebook Twitter LinkedIn More