Fast and Accurate Texture Recognition with Multilayer Convolution and Multifractal Analysis

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.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01064793
Contributor : H. Yahia <>
Submitted on : Wednesday, September 17, 2014 - 11:14:51 AM
Last modification on : Wednesday, November 14, 2018 - 1:54:07 PM
Long-term archiving on : Thursday, December 18, 2014 - 10:36:43 AM

File

eccv2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01064793, version 1

Collections

Citation

Hicham Badri, Hussein Yahia, K. 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⟩

Share

Metrics

Record views

933

Files downloads

922