Deep learning methodology for the identification of wood species using high-resolution macroscopic images and patch-voting
Authors:
- David Herrera-PoyatosDHDavid Herrera-Poyatos
- Andrés Herrera-PoyatosAHAndrés Herrera-Poyatos
- Rosana MontesRMRosana Montes
- Paloma de PalaciosPaloma de Palacios
- Luis G. EstebanLuis G. Esteban
- Alberto García IruelaAIAlberto García Iruela
- Francisco García FernándezFrancisco García Fernández
- Francisco HerreraFrancisco Herrera
Open Access
- 5 March 2026
- journal article
- research article
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (5) , 128
Abstract
Tools for automatic wood species identification are needed worldwide in order to support sustainable timber trade. This work explores the application of computer vision techniques to classify high-resolution macroscopic images of timber. The main challenge of this problem is that fine-grained patterns in timber are crucial in order to accurately identify wood species, and these patterns are not learned by convolutional neural networks (CNNs) trained on low resolution images. This work introduces the Timber Deep Learning Identification with Patch-based Inference Voting methodology, abbreviated TDLI-PIV methodology. This methodology exploits the concept of patching and the availability of high-resolution macroscopic images of timber in order to overcome the inherent challenges that CNNs face in timber identification. The TDLI-PIV methodology is able to capture fine-grained patterns in timber and, moreover, boosts robustness and prediction accuracy via a collaborative voting inference process. In this work we also introduce a new data set of marcroscopic images of timber, called GOIMAI-Phase-I, which has been obtained using optical magnification, and is openly published online in zenodo. Our experiments have assessed the performance of the TDLI-PIV methodology, including a comparison with other methodologies available in the literature, an exploration of data augmentation methods and the effect that the dataset size has on the accuracy of TDLI-PIV.Keywords
Funding Information
- Universidad de Granada
This publication has 33 references indexed in Scilit:
- A modified convolutional neural network architecture for diabetic retinopathy screening using SVDDApplied Soft Computing, 2022
- An effective and fast solution for classification of wood species: A deep transfer learning approachEcological Informatics, 2022
- Automated Detection of Covid-19 from Chest X-ray scans using an optimized CNN architectureApplied Soft Computing, 2021
- Amazon wood species classification: a comparison between deep learning and pre-designed featuresWood Science and Technology, 2021
- Wood species automatic identification from wood core images with a residual convolutional neural networkComputers and Electronics in Agriculture, 2021
- An automatic recognition system of Brazilian flora species based on textural features of macroscopic images of woodWood Science and Technology, 2020
- Wood species recognition through multidimensional texture analysisComputers and Electronics in Agriculture, 2018
- Patch-based self-adaptive matting for high-resolution image and videoThe Visual Computer, 2017
- Application of artificial neural networks as a predictive method to differentiate the wood of Pinus sylvestris L. and Pinus nigra Arn subsp. salzmannii (Dunal) FrancoWood Science and Technology, 2017
- Forest species recognition using macroscopic imagesMachine Vision and Applications, 2014