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

You might also read

Related Articles

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

Sort by
Same author

In the tracks of a whale: inferring size class, orientation and swimming speed from thermal flukeprints.

The Journal of experimental biology·2026
Same author

WildDrone: autonomous drone technology for monitoring wildlife populations.

Frontiers in robotics and AI·2026
Same author

A Simple Way to Reduce 3D Model Deformation in Smartphone Photogrammetry.

Sensors (Basel, Switzerland)·2023
Same author

Weed Classification Using Explainable Multi-Resolution Slot Attention.

Sensors (Basel, Switzerland)·2021
Same author

Robust Species Distribution Mapping of Crop Mixtures Using Color Images and Convolutional Neural Networks.

Sensors (Basel, Switzerland)·2021
Same author

A Novel Locating System for Cereal Plant Stem Emerging Points' Detection Using a Convolutional Neural Network.

Sensors (Basel, Switzerland)·2018

Related Experiment Video

Updated: May 11, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Seedling discrimination with shape features derived from a distance transform.

Thomas Mosgaard Giselsson1, Henrik Skov Midtiby, Rasmus Nyholm Jørgensen

  • 1Institute of Chemical Engineering, Biotechnology and Environmental Technology, University of Southern Denmark, Odense, Denmark. tgi@kbm.sdu.dk

Sensors (Basel, Switzerland)
|April 30, 2013
PubMed
Summary

Two novel shape feature generation methods improve plant seedling recognition. The Legendre Polynomial method achieved 97.5% accuracy, outperforming traditional features for distinguishing plant species.

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages
08:25

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages

Published on: June 2, 2020

Related Experiment Videos

Last Updated: May 11, 2026

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages
08:25

Imaging and Analysis of Tissue Orientation and Growth Dynamics in the Developing Drosophila Epithelia During Pupal Stages

Published on: June 2, 2020

Area of Science:

  • Plant science
  • Computer vision
  • Machine learning

Background:

  • Accurate plant seedling recognition is crucial for agriculture and ecology.
  • Traditional shape features can be limited in distinguishing similar plant species.

Purpose of the Study:

  • To develop and evaluate novel shape feature generation methods for improved plant seedling recognition.
  • To compare the performance of new features against existing methods.

Main Methods:

  • Two new approaches for generating shape features from plant silhouettes were proposed: resampling and Legendre Polynomial approximation.
  • Features were tested using four classifiers (k-Nearest Neighbor, Naive-Bayes, Linear SVM, Nonlinear SVM) on cornflower and nightshade samples.
  • Performance was assessed based on classification accuracy and compared to 21 established shape features.

Main Results:

  • The Legendre Polynomial feature set, comprising 10 numerical values, achieved the highest discrimination accuracy of 97.5%.
  • A comparative feature set of 21 common features yielded an accuracy of 92.5%.
  • The proposed Legendre Polynomial features demonstrated superior or competitive performance compared to existing methods.

Conclusions:

  • The Legendre Polynomial feature set offers a highly effective approach for plant seedling recognition.
  • Novel shape feature generation methods can significantly enhance the accuracy of plant identification systems.