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

Estimating Acrylamide and 5-Hydroxymethylfurfural Levels in Crackers Using Computer Vision: Effects on Consumer Acceptance.

Foods (Basel, Switzerland)·2026
Same author

In Silico Digital Breast Tomosynthesis Dataset for the Comparative Analysis of Deep Learning Models in Tumor Segmentation.

Journal of imaging informatics in medicine·2025
Same author

Sparse Regularization-Based Approach for Point Cloud Denoising and Sharp Features Enhancement.

Sensors (Basel, Switzerland)·2020
Same author

Characterization of spinal cord damage based on automatic video analysis of froglet swimming.

Biology open·2019
Same author

Long term three dimensional tracking of orthodontic patients using registered cone beam CT and photogrammetry.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2009

Related Experiment Video

Updated: Feb 21, 2026

Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.9K

A Method for Automatic Surface Inspection Using a Model-Based 3D Descriptor.

Carlos A Madrigal1, John W Branch2, Alejandro Restrepo3

  • 1Departamento de Ingeniería Electrónica, Instituto Tecnológico Metropolitano, Medellín 050013, Colombia. carlosmadrigal@itm.edu.co.

Sensors (Basel, Switzerland)
|October 5, 2017
PubMed
Summary

This study introduces a new 3D descriptor, the Model Point Feature Histogram (MPFH), for detecting small surface defects in manufactured parts. The MPFH method achieves high accuracy in recognizing defects from 3D point clouds.

Keywords:
3D inspection3D point clouddefects detectionsurface quality inspection

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.1K
Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

913

Related Experiment Videos

Last Updated: Feb 21, 2026

Precision Measurements and Parametric Models of Vertebral Endplates
10:35

Precision Measurements and Parametric Models of Vertebral Endplates

Published on: September 17, 2019

6.9K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

25.1K
Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads
07:58

Automatic Laser-based Geometry Capture for Finite Element Analysis of Weld Beads

Published on: July 25, 2025

913

Area of Science:

  • Computer Vision
  • Materials Science
  • Manufacturing

Background:

  • Sub-millimeter surface defects pose challenges for automated visual inspection, especially when lacking contrast in 2D images.
  • Topological deformations caused by defects are difficult to detect using traditional 2D imaging techniques.

Purpose of the Study:

  • To develop a robust method for recognizing surface defects in 3D point clouds.
  • To introduce a novel 3D local descriptor for improved defect detection and classification.

Main Methods:

  • Proposed a novel Model Point Feature Histogram (MPFH) descriptor for 3D point clouds.
  • Classified surface points into five primitive types for defect detection.
  • Projected primitive components to 2D images for feature extraction and defect recognition using a support vector machine.

Main Results:

  • The MPFH descriptor demonstrated robustness to noise and scale variations.
  • Achieved 95% accuracy in classifying 3D point clouds into primitives, outperforming state-of-the-art descriptors.
  • Reached a defect recognition rate of approximately 94% on diverse 3D defect datasets.

Conclusions:

  • The proposed MPFH descriptor is effective and discriminative for detecting challenging surface defects in 3D point clouds.
  • The integrated 3D-to-2D approach offers a reliable solution for automated visual inspection of surface imperfections.