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

Types of Errors: Detection and Minimization01:12

Types of Errors: Detection and Minimization

12.2K
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
12.2K
Constraints and Statical Determinacy01:26

Constraints and Statical Determinacy

1.1K
In structural engineering, the equilibrium of a system is not only determined by its equations of equilibrium but also with the help of constraints. Constraints refer to restrictions on the motion of a system. The proper combinations of constraints can minimize the total number of constraints needed to maintain a system in mechanical equilibrium. When this happens, the system is said to be statically determinate. For such systems, the unknown reaction supports can be estimated using equilibrium...
1.1K
Imperfections in Crystal Structure: Non-Stoichiometric Defects01:29

Imperfections in Crystal Structure: Non-Stoichiometric Defects

92
Non-stoichiometric defects refer to a type of defect in the crystal structure of a compound where the ratio of its constituent elements deviates from the ideal stoichiometric ratio. There are two main types of non-stoichiometric defects: metal excess defects and metal deficiency defects.Metal excess defects occur when there is a slight surplus of metal ions than what is required by the stoichiometric ratio of the compound. For example, heating a sodium chloride crystal in sodium vapor results...
92
Imperfections in Crystal Structure: Point, Line and Plane Defects01:25

Imperfections in Crystal Structure: Point, Line and Plane Defects

103
A perfect crystal, in theory, has a uniform structure with the same unit cell and lattice points throughout. However, any deviation from this periodic arrangement is known as an imperfection or defect. These defects can be categorized into three types: point, line, and plane defects.Point defects occur when there is a deviation from the ideal due to missing atoms, displaced atoms, or additional atoms. These imperfections might occur due to imperfect packing during crystallization or because of...
103
Imperfections in Crystal Structure: Stoichiometric Point Defects01:26

Imperfections in Crystal Structure: Stoichiometric Point Defects

91
Schottky defects arise when some lattice points in a crystal, such as those in NaCl, remain unoccupied, creating lattice vacancies without disturbing the overall electrical neutrality of the crystal. This defect is common in ionic crystals where the positive and negative ions are similar in size, as seen in sodium chloride and cesium chloride. The presence of Schottky defects enables the crystal to conduct electricity to a small extent through an ionic mechanism. Electric fields cause nearby...
91
Stereotype Content Model02:16

Stereotype Content Model

15.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.7K

You might also read

Related Articles

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

Sort by
Same author

An Improved YOLOv9 Based Object Detection with Attention Mechanism for Personal Protective Equipment.

Sensors (Basel, Switzerland)·2026
Same author

VibGrasp: Spatiotemporal Vibration Based Multimodal Haptic Rendering with a Lightweight Exo-Glove for 3D Shape Perception.

IEEE transactions on haptics·2026
Same author

Annual trends in heterozygosity of Korea native cattle (Hanwoo) based on microsatellite markers.

Animal bioscience·2026
Same author

"Same Calories, Different Foods" - What do you choose? The role of construal level and age in shaping food choices.

Frontiers in psychology·2025
Same author

Bidirectional Asymmetric Frequency Conversion in Nonlinear Phononic Crystals.

Physical review letters·2025
Same author

The Influence of New Media Literacy on Brand Engagement: Mediating Effects of Perceived Interactivity and Openness and the Moderating Effect of Age.

Behavioral sciences (Basel, Switzerland)·2025

Related Experiment Video

Updated: Apr 11, 2026

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
05:47

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

Published on: August 29, 2025

626

CLARIS: Control-based language-guided realistic imperfection synthesis.

Eunho Kim1, Jongpil Jeong2

  • 1Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, 16419, Suwon, Gyeonggi-do, Republic of Korea.

Scientific Reports
|April 9, 2026
PubMed
Summary

This study introduces CLARIS, a new method for generating realistic defect images in manufacturing. It addresses data imbalance by creating high-quality synthetic defects guided by natural language and 3D constraints.

Keywords:
Anomaly detectionConditional diffusion modelImage generationLanguage-guided generationParameter-efficient fine-tuningSmart manufacturing

More Related Videos

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
11:54

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

5.3K
Technical Aspect of the Automated Synthesis and Real-Time Kinetic Evaluation of [11C]SNAP-7941
09:50

Technical Aspect of the Automated Synthesis and Real-Time Kinetic Evaluation of [11C]SNAP-7941

Published on: April 28, 2019

8.1K

Related Experiment Videos

Last Updated: Apr 11, 2026

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
05:47

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

Published on: August 29, 2025

626
Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface
11:54

Real-Time Proxy-Control of Re-Parameterized Peripheral Signals using a Close-Loop Interface

Published on: May 8, 2021

5.3K
Technical Aspect of the Automated Synthesis and Real-Time Kinetic Evaluation of [11C]SNAP-7941
09:50

Technical Aspect of the Automated Synthesis and Real-Time Kinetic Evaluation of [11C]SNAP-7941

Published on: April 28, 2019

8.1K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Manufacturing Technology

Background:

  • Automated vision inspection in manufacturing faces challenges with imbalanced datasets, having abundant normal data and scarce defective data.
  • High-yield manufacturing processes exacerbate this data imbalance, hindering effective defect detection model training.

Purpose of the Study:

  • To develop a novel framework, CLARIS (Control-based Language-guided Realistic Imperfection Synthesis), for generating physically consistent, high-quality defect images.
  • To overcome the data imbalance problem in automated vision inspection by synthesizing realistic defective data.

Main Methods:

  • CLARIS combines a Vision-Language Model (VLM) for interpreting user instructions and generating text prompts/defect masks.
  • ControlNet is used with normal maps as constraints to ensure synthesized defects conform to object geometry and surface curvature.
  • Textual Inversion (TI) and Low-Rank Adaptation (LoRA) are employed for efficient learning of specific defect characteristics with minimal parameters.

Main Results:

  • The framework was evaluated on the MVTec Anomaly Detection (MVTec AD) dataset across 15 categories.
  • Achieved an average Kernel Inception Distance (KID) of 11.07, indicating high-quality image generation.
  • Obtained an Inception Score (IS) of 1.63 and an intra-cluster pairwise LPIPS distance (IC-LPIPS) of 0.27, demonstrating good diversity and consistency.

Conclusions:

  • CLARIS effectively generates realistic and physically consistent defect images by integrating language guidance with 3D structural constraints.
  • The proposed framework offers a viable solution for addressing data imbalance in automated visual inspection for manufacturing.
  • The use of VLM, ControlNet, TI, and LoRA enables efficient and tailored synthesis of defect data for improved anomaly detection.