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

Outliers and Influential Points01:08

Outliers and Influential Points

6.5K
An outlier is an observation of data that does not fit the rest of the data. It is sometimes called an extreme value. When you graph an outlier, it will appear not to fit the pattern of the graph. Some outliers are due to mistakes (for example, writing down 50 instead of 500), while others may indicate that something unusual is happening. Outliers are present far from the least squares line in the vertical direction. They have large "errors," where the "error" or residual is the...
6.5K
What Are Outliers?01:12

What Are Outliers?

5.4K
Outliers are observed data points that are far from the least squares line. They have unusual values and need to be examined carefully. Though an outlier may result from erroneous data, at other times, it may hold valuable information about the population under study and should be included in the data. Hence, it is crucial to examine what causes a data point to be an outlier.
The z score is used to find outliers or unusual values. It should be noted that any values beyond -2 and +2 are...
5.4K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

7.1K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
7.1K
Elastic Collisions: Case Study01:15

Elastic Collisions: Case Study

20.8K
Elastic collision of a system demands conservation of both momentum and kinetic energy. To solve problems involving one-dimensional elastic collisions between two objects, the equations for conservation of momentum and conservation of internal kinetic energy can be used. For the two objects, the sum of momentum before the collision equals the total momentum after the collision. An elastic collision conserves internal kinetic energy, and so the sum of kinetic energies before the collision equals...
20.8K

You might also read

Related Articles

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

Sort by
Same author

An Empirical Study of Federated Learning on IoT-Edge Devices: Resource Allocation and Heterogeneity.

IEEE transactions on neural networks and learning systems·2025
Same author

Text-guided RGB-P grasp generation.

PeerJ. Computer science·2025
Same author

Resilient consensus control for networked robotic manipulators under actuator faults and deception attacks.

ISA transactions·2025
Same author

SVD-Based Mind-Wandering Prediction from Facial Videos in Online Learning.

Journal of imaging·2024
Same author

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation.

Sensors (Basel, Switzerland)·2023
Same author

Ultrasonic testing of rivet in multilayer structure using a convolutional neural network on edge device.

Science progress·2023

Related Experiment Video

Updated: Feb 25, 2026

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

43.7K

Efficient industrial point cloud anomaly detection via spatial context aggregation and selective anomalous feature

Dinh-Cuong Hoang1, Phan Xuan Tan2, Anh-Nhat Nguyen3

  • 1Greenwich Vietnam, FPT University, Hanoi, 10000, Vietnam. cuonghd12@fe.edu.vn.

Scientific Reports
|February 23, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a new framework for automated 3D surface defect detection, improving accuracy by addressing context ambiguity and data limitations in industrial scans. The method enhances product quality through efficient and reliable anomaly detection.

Keywords:
Defect detectionIndustrial anomaly detectionIndustrial anomaly segmentation

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Related Experiment Videos

Last Updated: Feb 25, 2026

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

43.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.1K

Area of Science:

  • Manufacturing Engineering
  • Computer Vision
  • Artificial Intelligence

Background:

  • Automated surface defect detection in 3D parts is crucial for manufacturing quality and safety.
  • Existing methods face challenges with geometric context ambiguity, domain mismatch in industrial scans, and limited defect data.
  • These limitations hinder reliable and efficient anomaly detection in real-world manufacturing scenarios.

Purpose of the Study:

  • To propose a novel single-forward-pass framework for point cloud anomaly detection in 3D parts.
  • To overcome challenges in geometric context ambiguity, domain mismatch, and data scarcity for industrial surface defect detection.
  • To achieve efficient and accurate automated detection of surface defects on complex 3D manufactured parts.

Main Methods:

  • Developed a framework with Spatial Context Aggregation using optimal-transport alignment for global context.
  • Implemented a Feature Adaptor (MLP) to fine-tune Point-MAE embeddings for industrial scan characteristics.
  • Introduced a Selective Anomalous Feature Generator to synthesize hard negatives, reducing reliance on defect labels.

Main Results:

  • Achieved significant improvements on the Real3D-AD benchmark: 2.8% (point-level AUROC), 5.7% (point-level AUPR), 3.0% (object-level AUROC), and 3.5% (object-level AUPR).
  • Demonstrated robust performance on the Industrial3D-AD dataset with realistic sensor noise and reflective materials (2.9%/5.3% point-level, 2.8%/3.3% object-level).
  • The proposed pipeline delivers dense per-point anomaly scores at a high inference speed of up to 13.5 FPS.

Conclusions:

  • The novel framework effectively addresses key challenges in 3D surface defect detection for manufacturing.
  • The proposed modules enhance context understanding, adapt features to industrial data, and mitigate data scarcity issues.
  • This approach offers a promising solution for improving automated quality control in manufacturing through efficient and accurate anomaly detection.