ML Anthology

A Handcrafted Normalized-Convolution Network for Texture Classification

Ngoc-Son Vu, Vu-Lam Nguyen, Philippe-Henri Gosselin
ICCVW 2017 pp. 1238-1245
doi:10.1109/ICCVW.2017.149 /iccvw/2017/vu2017iccvw-handcrafted/

Abstract

In this paper, we propose a Handcrafted Normalized-Convolution Network (NmzNet) for efficient texture classification. NmzNet is implemented by a three-layer normalized convolution network, which computes successive normalized convolution with a predefined filter bank (Gabor filter bank) and modulus non-linearities. Coefficients from different layers are aggregated by Fisher Vector aggregation to form the final discriminative features. The results of experimental evaluation on three texture datasets UIUC, KTH-TIPS-2a, and KTH-TIPS-2b indicate that our proposed approach achieves the good classification rate compared with other handcrafted methods. The results additionally indicate that only a marginal difference exists between the best classification rate of recent frontiers CNN and that of the proposed method on the experimented datasets.

PDF ICCVW Semantic Scholar

Cite

Text

Vu et al. "A Handcrafted Normalized-Convolution Network for Texture Classification." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.149

Markdown

[Vu et al. "A Handcrafted Normalized-Convolution Network for Texture Classification." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/vu2017iccvw-handcrafted/) doi:10.1109/ICCVW.2017.149

BibTeX

@inproceedings{vu2017iccvw-handcrafted,
  title     = {{A Handcrafted Normalized-Convolution Network for Texture Classification}},
  author    = {Vu, Ngoc-Son and Nguyen, Vu-Lam and Gosselin, Philippe-Henri},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {1238-1245},
  doi       = {10.1109/ICCVW.2017.149},
  url       = {https://mlanthology.org/iccvw/2017/vu2017iccvw-handcrafted/}
}