Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Design of potent, proteolytically stable stapled lipopeptide analogues of BimBH3 as PTP1B inhibitors for diabetes therapy.

European journal of medicinal chemistry·2026

Same author

Dual Conjugation of Long- and Medium-Chain Fatty Acids to BimBH3 Peptide Yields Ultra Long-Acting Inhibitors of Intracellular PTPN1/2.

Journal of medicinal chemistry·2025

Same author

Glycosylation Modification Balances the Aqueous Solubility of Lipidated Peptides and Facilitates Their Biostability.

Bioconjugate chemistry·2025

Same author

Fatty acid conjugated BimBH3 analogues with d‑amino acid substitution as PTPN1 inhibitors with enhanced activity, biostability and orally available potency for the treatment of diabetes.

Bioorganic & medicinal chemistry·2025

Same author

Site-Specifically Modified Peptide Inhibitors of Protein Tyrosine Phosphatase 1B and T-Cell Protein Tyrosine Phosphatase with Enhanced Stability and Improved In Vivo Long-Acting Activity.

ACS pharmacology & translational science·2024

Same author

A Retrospective Study of Long-Term Clinical Outcomes in Patients with Chronic Hepatitis C Treated with Interferon and Ribavirin.

Discovery medicine·2023

Search research articles

Related Experiment Video

Updated: Sep 2, 2025

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

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

Published on: December 15, 2023

A pixel-wise framework based on convolutional neural network for surface defect detection.

¹China Telecom Corporation Limited Research Institute, Beijing, 102209, China.

Mathematical Biosciences and Engineering : MBE

|August 9, 2022

Summary

This study introduces a new convolutional neural network (CNN) method for detecting surface defects in strip steel. The advanced framework improves accuracy in identifying challenging defects with low contrast and varied textures.

Keywords:

Surface defect detection convolutional neural network cross integrate multi-scale context information pixel-wise detection

More Related Videos

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Sep 2, 2025

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

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

Published on: December 15, 2023

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Materials Science
Computer Vision
Artificial Intelligence

Background:

Automatic surface defect detection is crucial for real-time quality control in industrial settings.
Existing systems struggle with defects characterized by low contrast, diverse textures, and complex geometric structures.
Accurate identification of these challenging defects remains a significant hurdle in strip steel manufacturing.

Purpose of the Study:

To propose a novel pixel-wise detection framework for strip steel surface defects.
To enhance the accuracy and robustness of automatic surface defect detection systems.
To address the challenges posed by low-contrast, multi-textured, and geometrically complex defects.

Main Methods:

A convolutional neural network (CNN) based framework for pixel-wise defect detection.
Extraction of salient features using a pre-trained backbone network.
A contextual weighting module employing diverse convolutional kernels for multi-scale feature extraction and defect perception.
Cross-integration for feature information complementation and enhanced contextual understanding.

Main Results:

The proposed method achieved superior performance on a strip steel surface defect dataset.
Demonstrated high accuracy with a Mean Absolute Error (MAE) of 0.0396.
Achieved a high F-score of 0.8485, indicating effective defect detection capabilities.

Conclusions:

The developed CNN framework effectively addresses the complexities of strip steel surface defect detection.
The method significantly outperforms previous state-of-the-art approaches.
This research offers a promising solution for improving real-time quality inspection in strip steel production.