Jove
Visualize
Contact Us

Related Concept Videos

Two-Dimensional Force System: Problem Solving01:29

Two-Dimensional Force System: Problem Solving

992
Solving problems related to two-dimensional force systems is an essential aspect of mechanics and engineering. By applying the principles of vector analysis and force equilibrium, one can determine the effect of multiple forces acting on an object in a two-dimensional space.
The first step to solving a two-dimensional force system problem is to draw a free-body diagram of the object under consideration. This diagram helps identify all the external forces acting on the object, including their...
992

You might also read

Related Articles

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

Sort by
Same author

Enhancing Grapevine Node Detection to Support Pruning Automation: Leveraging State-of-the-Art YOLO Detection Models for 2D Image Analysis.

Sensors (Basel, Switzerland)·2024
Same author

Visible and Thermal Image-Based Trunk Detection with Deep Learning for Forestry Mobile Robotics.

Journal of imaging·2021
Same author

Design and Comparison of Image Hashing Methods: A Case Study on Cork Stopper Unique Identification.

Journal of imaging·2021
See all related articles
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 Experiment Video

Updated: Oct 22, 2025

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback
05:43

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback

Published on: May 23, 2019

5.6K

A Comparative Analysis for 2D Object Recognition: A Case Study with Tactode Puzzle-Like Tiles.

Daniel Silva1,2, Armando Sousa1,3, Valter Costa4

  • 1Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal.

Journal of Imaging
|August 30, 2021
PubMed
Summary
This summary is machine-generated.

VGG16 achieved the highest accuracy for Tactode tile recognition, outperforming other machine learning and deep learning methods. HOG and SVM offered the fastest execution times, making VGG16 the optimal choice for minimizing errors.

Keywords:
2D object recognitionHOGMobileNetResNetSSDSVMVGGYOLOcomputer visionmachine learning

More Related Videos

Investigating the Effect of Visual Imagery and Learning Shape-Audio Regularities on Bouba and Kiki
07:31

Investigating the Effect of Visual Imagery and Learning Shape-Audio Regularities on Bouba and Kiki

Published on: September 13, 2019

10.3K
Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
06:36

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

Published on: October 18, 2024

1.2K

Related Experiment Videos

Last Updated: Oct 22, 2025

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback
05:43

Applying Incongruent Visual-Tactile Stimuli during Object Transfer with Vibro-Tactile Feedback

Published on: May 23, 2019

5.6K
Investigating the Effect of Visual Imagery and Learning Shape-Audio Regularities on Bouba and Kiki
07:31

Investigating the Effect of Visual Imagery and Learning Shape-Audio Regularities on Bouba and Kiki

Published on: September 13, 2019

10.3K
Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
06:36

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

Published on: October 18, 2024

1.2K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Recognition

Background:

  • Object recognition is crucial for identifying elements in images.
  • This study focuses on Tactode tile recognition, comparing various classification techniques.
  • A diverse range of methods, from traditional machine learning to deep learning, were evaluated.

Purpose of the Study:

  • To conduct a comparative analysis of different classification methods for Tactode tile recognition.
  • To identify the most effective and efficient method for this specific object recognition task.
  • To benchmark the performance of various algorithms on custom datasets.

Main Methods:

  • Machine learning methods: Histogram of Oriented Gradients (HOG) with Support Vector Machines (SVM).
  • Deep learning methods: Convolutional Neural Networks (CNNs) including VGG16, VGG19, ResNet152, MobileNetV2, Single Shot Detector (SSD), and YOLOv4.
  • Handcrafted feature matching: Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Binary Robust Independent Elementary Features (BRIEF) with Rotated Features (BRISK), and Oriented FAST and Rotated BRIEF (ORB).
  • Template matching techniques were also assessed.

Main Results:

  • VGG16 and VGG19 demonstrated superior accuracy, with VGG16 achieving 99.96% on the small dataset and 99.95% on the large dataset.
  • HOG and SVM provided the fastest execution times (0.323s and 0.232s) while maintaining high accuracy (99.93% and 99.86%).
  • SURF, ORB, and BRISK showed strong performance, whereas SIFT and the deep learning models SSD and YOLOv4 were less effective for this task.

Conclusions:

  • VGG16 is identified as the optimal method for Tactode tile recognition due to its minimal misclassification rate.
  • While VGG16 offers the best accuracy, HOG and SVM present a compelling alternative for applications prioritizing speed.
  • The study highlights the varying effectiveness of different object recognition approaches depending on the specific application and dataset.