ACD-YOLO: Improved YOLOv5-based method for steel surface defects detection

Since the quality of steel is of paramount importance in modern production, the defects detection of steel surface is significantly crucial. In this field, two‐stage detection algorithms have encountered issues about low detection speed, while one‐stage detection algorithms have room for improvement in detection accuracy. How to trade‐off between accuracy and speed of detection to better meet the demands of industrial production remains a challenge. To address this problem, this paper proposes a You Only Look Once version 5 (YOLOv5)‐based improved method ACD‐YOLO. ACD‐YOLO model incorporates anchors optimization, context augmentation module, and efficient convolution operators. In anchor optimization, the boundaries of anchors are optimized using an improved genetic algorithm. Moreover, to improve detection accuracy, a context augmentation module is incorporated into both the head and the backbone end of the network. Additionally, efficient convolution operators are adopted to address the increase of computation complexity caused by the context augmentation module. Experimental results show that ACD‐YOLO achieves mean average precision of 79.3%, with frames per second of 72. Compared to reference methods, ACD‐YOLO achieves the best balance between accuracy and speed of detection, and is more suitable for practice industrial production.

• Publication year

  2023

• Venue

  IET Image Processing

• Publication date

  2023-11-11

• Fields of study

  Materials Science, Computer Science, Engineering

• Identifiers
  DOI 10.1049/ipr2.12983
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• RDD-YOLO: A modified YOLO for detection of steel surface defects

  2023cited by this paper
• Steel Surface Defect Detection Based on Improved YOLOV5 Algorithm

  2022cited by this paper
• A steel surface defect detection algorithm based on improved YOLOv5

  2022cited by this paper
• DCC-CenterNet: A rapid detection method for steel surface defects

  2021cited by this paper
• Triplet-Graph Reasoning Network for Few-Shot Metal Generic Surface Defect Segmentation

  2021cited by this paper
• A Beneficial Dual Transformation Approach for Deep Learning Networks Used in Steel Surface Defect Detection

  2021cited by this paper
• A review on genetic algorithm: past, present, and future

  2020cited by this paper
• Surface defect classification of steels with a new semi-supervised learning method

  2019cited by this paper
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  2015cited by this paper
• Review of vision-based steel surface inspection systems

  2014cited by this paper
• Automatic Defect Detection on Hot-Rolled Flat Steel Products

  2013cited by this paper
• A High-Accuracy Algorithm for Surface Defect Detection of Steel Based on DAG-SVM

  2013cited by this paper
• Process knowledge based multi-class support vector classification (PK-MSVM) approach for surface defects in hot rolling

  2011cited by this paper
• Particle Swarm Optimization with Adaptive Mutation

  2009cited by this paper
• A Surface Inspection Machine Vision System that Includes Fractal Texture Analysis

  2008cited by this paper
• Pulsed magnetic flux leakage techniques for crack detection and characterisation

  2006cited by this paper
• Computation of three-dimensional electromagnetic field in the eddy-current testing of steel pipes

  1988cited by this paper
• A Real-Time Automated Visual Inspection System for Hot Steel Slabs

  1983cited by this paper
• A YOLOV8-BASED APPROACH FOR STEEL PLATE SURFACE DEFECT DETECTION

  year unknowncited by this paper

• ELG-YOLO: Multi-Scale Feature Fusion and Attention Mechanisms for Enhanced Steel Surface Defect Detection

  2026cites this paper
• LESSDD-Net: A Lightweight and Efficient Steel Surface Defect Detection Network Based on Feature Segmentation and Partially Connected Structures

  2026cites this paper
• Boosting lightweight object detection with enhanced feature fusion and optimized receptive field

  2026cites this paper
• WBS-YOLOv8: A Lightweight Infrared Object Detection Algorithm for Nighttime Autonomous Driving

  2025cites this paper
• ELS-YOLO: Efficient Lightweight YOLO for Steel Surface Defect Detection

  2025cites this paper
• LMFL-YOLO: a lightweight multi-scale fusion and localization-enhanced YOLO network for steel surface defect detection

  2025cites this paper
• Li-YOLO Net: a lightweight steel defect detection framework with dynamic feature selection and task alignment

  2025cites this paper
• Surface Defect Detection of Steel Based on Improved YOLOv5s

  2025cites this paper
• Predictive Failure Detection in Cloud Infrastructure Using Multivariate Telemetry Log Analysis with Temporal Convolution and Attention-Based Deep Learning

  2025cites this paper
• Towards Intelligent Manufacturing: Deep Learning Approaches for Automated Visual Inspection and Fault Diagnosis

  2025influential citation
• Real-time detection of cracks: improved YOLOv8 network applied to wooden structure of residential historic buildings

  2025cites this paper
• EAD-YOLOv10: Lightweight Steel Surface Defect Detection Algorithm Research Based on YOLOv10 Improvement

  2025cites this paper
• ECF-YOLOv7-Tiny: Improving Feature Fusion and the Receptive Field for Lightweight Object Detectors

  2025influential citation
• Towards Safer Cities: AI-Powered Infrastructure Fault Detection Based on YOLOv11

  2025cites this paper
• Surface defect detection on bolt surface using a real-time fine-tuned YOLOv6 model

  2025cites this paper
• Automated subway touch button detection using image process

  2024cites this paper
• Steel Surface Defect Detection Based on YOLOv8-TLC

  2024cites this paper
• Research on Surface Defect Detection of Strip Steel Based on Improved YOLOv7

  2024cites this paper
• SCFNet: Lightweight Steel Defect Detection Network Based on Spatial Channel Reorganization and Weighted Jump Fusion

  2024cites this paper
• Research on adaptive object detection via improved HSA-YOLOv5 for raspberry maturity detection

  2024cites this paper
• GDB-YOLOv5s: Improved YOLO-based model for ship detection in SAR images

  2024cites this paper