Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Softwoods and Hardwoods

Softwoods and Hardwoods

Softwoods and hardwoods, derived from different types of trees, are distinguished by their leaf structures and cellular compositions, each serving unique purposes in construction and manufacturing. Softwoods come from cone-bearing trees with needle-like leaves and are predominantly composed of longitudinal cells called tracheids and a smaller proportion of radial cells known as rays. Due to their cellular structure, softwoods are commonly used in construction for structural frames, sheathing,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Bilateral Defect Cutting Strategy for Sawn Timber Based on Artificial Intelligence Defect Detection Model.

Sensors (Basel, Switzerland)·2024

Same author

Super-Resolution Reconstruction of Speckle Images of Engineered Bamboo Based on an Attention-Dense Residual Network.

Sensors (Basel, Switzerland)·2022

Same author

Detection Method for Bolted Connection Looseness at Small Angles of Timber Structures based on Deep Learning.

Sensors (Basel, Switzerland)·2021

Same author

Research on the Prediction of Green Plum Acidity Based on Improved XGBoost.

Sensors (Basel, Switzerland)·2021

Same author

Online Color Classification System of Solid Wood Flooring Based on Characteristic Features.

Sensors (Basel, Switzerland)·2021

Same author

[Preparation and identification of monoclonal antibody against Homo sapiens hemoglobin alpha 2 (HBA2)].

Zhongguo shi yan xue ye xue za zhi·2007

Search research articles

Related Experiment Video

Updated: Nov 3, 2025

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

A Sawn Timber Tree Species Recognition Method Based on AM-SPPResNet.

Fenglong Ding¹, Ying Liu¹, Zilong Zhuang¹

¹College of Mechanical and Electrical Engineering, Nanjing Forestry University, Nanjing 210037, China.

Sensors (Basel, Switzerland)

|June 2, 2021

Summary

Accurate tree species identification for sawn timber is crucial for quality manufacturing. An optimized ResNet model combined with Support Vector Machine (SVM) achieved over 99% accuracy in identifying timber species from images.

Keywords:

attention mechanism deep learning recognition of sawn timber spatial pyramid pooling

More Related Videos

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Published on: August 29, 2019

A Method for Quantifying Foliage-Dwelling Arthropods

A Method for Quantifying Foliage-Dwelling Arthropods

Published on: October 20, 2019

Related Experiment Videos

Last Updated: Nov 3, 2025

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Leaf Area Index Estimation Using Three Distinct Methods in Pure Deciduous Stands

Published on: August 29, 2019

A Method for Quantifying Foliage-Dwelling Arthropods

A Method for Quantifying Foliage-Dwelling Arthropods

Published on: October 20, 2019

Area of Science:

Wood science
Computer vision
Machine learning

Background:

Sawn timber is vital in furniture, decoration, and construction.
Different tree species have distinct properties affecting material use and product quality.
Accurate timber identification is essential for optimal material utilization.

Purpose of the Study:

To develop an optimized deep learning model for accurate tree species identification of sawn timber using image data.
To improve feature extraction from timber images for enhanced classification.

Main Methods:

An optimized ResNet101 architecture (AM-SPPResNet) incorporating spatial pyramid pooling and attention mechanisms was developed.
Feature vectors were extracted using the improved convolutional layers.
Support Vector Machine (SVM) and XGBoost classifiers were trained on these feature vectors.

Main Results:

The AM-SPPResNet model achieved high performance in timber species recognition.
The SVM classifier with a linear kernel, trained on extracted features, yielded the best results.
The final model achieved an F1 score and overall accuracy exceeding 99% for all sample types.

Conclusions:

The proposed AM-SPPResNet combined with SVM offers a highly accurate method for sawn timber species identification.
This approach significantly improves accuracy compared to traditional methods, with up to a 12% increase.
The findings support the effective application of advanced machine learning in wood science and industry.