Exploring Local Graphs via Random Encoding for Texture Representation Learning

Ricardo T. Fares, Luan B. Guerra, Lucas C. Ribas

2025

Abstract

Despite many graph-based approaches being proposed to model textural patterns, they not only rely on a large number of parameters, culminating in a large search space, but also model a single, large graph for the entire image, which often overlooks fine-grained details. This paper proposes a new texture representation that utilizes a parameter-free micro-graph modeling, thereby addressing the aforementioned limitations. Specifically, for each image, we build multiple micro-graphs to model the textural patterns, and use a Randomized Neural Network (RNN) to randomly encode their topological information. Following this, the network’s learned weights are summarized through distinct statistical measures, such as mean and standard deviation, generating summarized feature vectors, which are combined to form our final texture representation. The effectiveness and robustness of our proposed approach for texture recognition was evaluated on four datasets: Outex, USP-tex, Brodatz, and MBT, outperforming many literature methods. To assess the practical application of our method, we applied it to the challenging task of Brazilian plant species recognition, which requires microtex-ture characterization. The results demonstrate that our new approach is highly discriminative, indicating an important contribution to the texture analysis field.

Paper Citation

in Harvard Style

Fares R., Guerra L. and Ribas L. (2025). Exploring Local Graphs via Random Encoding for Texture Representation Learning. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 200-209. DOI: 10.5220/0013315500003912

in Bibtex Style

@conference{visapp25,
author={Ricardo Fares and Luan Guerra and Lucas Ribas},
title={Exploring Local Graphs via Random Encoding for Texture Representation Learning},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={200-209},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013315500003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Exploring Local Graphs via Random Encoding for Texture Representation Learning
SN - 978-989-758-728-3
AU - Fares R.
AU - Guerra L.
AU - Ribas L.
PY - 2025
SP - 200
EP - 209
DO - 10.5220/0013315500003912
PB - SciTePress