Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Softwoods and Hardwoods01:28

Softwoods and Hardwoods

276
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,...
276
Introduction to Wood01:19

Introduction to Wood

364
Wood, derived from trees, is a versatile and widely used construction material. Trees feature a trunk surrounded by a protective layer of dead bark. Beneath this outer layer lies the living bark, followed by the cambium, and then the sapwood which transitions into heartwood as it matures. At the center of the trunk is the pith. The age of a tree can be discerned by examining its growth rings, which are concentric bands visible in the trunk's cross-section.
The structural integrity of the...
364
Lumber01:19

Lumber

196
Lumber is derived from logs which are harvested, debarked, and processed into long pieces with a rectangular cross-section. The transformation of logs into lumber involves multiple steps, beginning with an automated saw that slices the log into slabs. These slabs are then transported via a conveyor belt to smaller saws, where they are cut into square-edged pieces of specific widths.
Initially, the surfaces of these lumber pieces are rough, and their dimensions may vary slightly from one end to...
196
Structural Properties and Dimensions of Lumber01:21

Structural Properties and Dimensions of Lumber

208
Wood's structural properties derive from fibers aligned along the tree's length, contributing significantly to its mechanical strength. Wood exhibits up to twenty times greater tensile strength along these fibers compared to across them, and generally shows better performance under compression than tension. The length of fibers varies, with hardwoods having fibers around one twenty-fifth inch long and softwoods ranging from one-eighth to one-third inch.
The strength characteristics of...
208

You might also read

Related Articles

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

Sort by
Same author

Efficient Automatic Pollen Recognition From Fossil Pollen Samples: A High-Resolution Example Record From Palaeolake Kieshofer Moor, Northeastern Germany.

Ecology and evolution·2026
Same author

Hidden radiation legacy revealed in Scots pine's xylem structure and hydraulic function after the Chornobyl accident.

The Science of the total environment·2026
Same author

No seed size-number trade-off in European beech: climate governs investment per seed.

The New phytologist·2026
Same author

Intra-annual transfer of hydrogen and oxygen isotopic signals from water and sugar precursors to tree rings: Processes and mechanisms.

The New phytologist·2026
Same author

Mind the vessel: towards a unified framework of dendroecology and ecophysiology for understanding angiosperm tree functioning in European temperate climates.

Tree physiology·2026
Same author

Early onset of stomatal closure confounds current interpretations and applications of iso-/anisohydry theory.

The New phytologist·2025

Related Experiment Video

Updated: Oct 12, 2025

Author Spotlight: Advancements in X-ray CT Tool Chain for Tree Core Analysis
06:56

Author Spotlight: Advancements in X-ray CT Tool Chain for Tree Core Analysis

Published on: September 22, 2023

1.3K

Mask, Train, Repeat! Artificial Intelligence for Quantitative Wood Anatomy.

Giulia Resente1, Alexander Gillert2, Mario Trouillier1

  • 1Institute of Botany and Landscape Ecology, Ernst Moritz Arndt University Greifswald, Greifswald, Germany.

Frontiers in Plant Science
|November 22, 2021
PubMed
Summary

Deep Convolutional Neural Networks (DCNNs) advance quantitative wood anatomy (QWA) analysis by improving cell detection and measurement accuracy. Mask-RCNN shows high potential for QWA research, outperforming other methods in specific applications.

Keywords:
F1 scoreROXASartificial intelligencedeep learninglumen areawood anatomy

More Related Videos

A Technical Perspective in Modern Tree-ring Research - How to Overcome Dendroecological and Wood Anatomical Challenges
09:33

A Technical Perspective in Modern Tree-ring Research - How to Overcome Dendroecological and Wood Anatomical Challenges

Published on: March 5, 2015

29.3K
Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices
07:40

Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices

Published on: March 10, 2023

2.4K

Related Experiment Videos

Last Updated: Oct 12, 2025

Author Spotlight: Advancements in X-ray CT Tool Chain for Tree Core Analysis
06:56

Author Spotlight: Advancements in X-ray CT Tool Chain for Tree Core Analysis

Published on: September 22, 2023

1.3K
A Technical Perspective in Modern Tree-ring Research - How to Overcome Dendroecological and Wood Anatomical Challenges
09:33

A Technical Perspective in Modern Tree-ring Research - How to Overcome Dendroecological and Wood Anatomical Challenges

Published on: March 5, 2015

29.3K
Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices
07:40

Advanced Workflow for Taking High-Quality Increment Cores - New Techniques and Devices

Published on: March 10, 2023

2.4K

Area of Science:

  • Ecology
  • Computer Science
  • Botany
  • Artificial Intelligence

Background:

  • Quantitative wood anatomy (QWA) analysis faces challenges in cell detection, feature variability, and sample quality.
  • Deep Convolutional Neural Networks (DCNNs) offer advanced capabilities for automatic image analysis.
  • Previous studies have utilized image analysis techniques for QWA, but DCNNs present a novel approach.

Purpose of the Study:

  • To apply a DCNN, specifically a Mask-RCNN architecture, to automate and improve quantitative wood anatomical analyses.
  • To evaluate the performance of the developed DCNN algorithm against existing methods like U-Net and ROXAS.
  • To assess the accuracy of cell detection and measurement provided by the DCNN.

Main Methods:

  • A Deep Convolutional Neural Network (DCNN) with a Mask-RCNN architecture was developed in Python using Pytorch.
  • The DCNN was trained using images of transversal wood anatomical sections and manually created ground truth data.
  • Performance was evaluated by comparing Mask-RCNN outputs with U-Net and ROXAS, assessing cell recognition and measurement accuracy.

Main Results:

  • The Mask-RCNN algorithm successfully detected and segmented cells, providing measurement accuracy information.
  • Mask-RCNN demonstrated higher accuracy in detecting target cells and segmenting lumen areas for angiosperms compared to U-Net and ROXAS.
  • ROXAS performed best for conifers, while U-Net generally underperformed compared to the other two algorithms.

Conclusions:

  • Deep learning, particularly DCNNs like Mask-RCNN, significantly enhances quantitative wood anatomical analyses by overcoming manual limitations.
  • The developed Mask-RCNN tool offers a flexible and accurate approach for QWA, saving analysis time.
  • Future QWA software should incorporate DCNNs, allowing for model retraining to adapt to diverse wood anatomical datasets.