Computer-Vision-Based Product Quality Inspection and Novel Counting System

In this study, we aimed to enhance the accuracy of product quality inspection and counting in the manufacturing process by integrating image processing and human body detection algorithms. We employed the SIFT algorithm combined with traditional image comparison metrics such as SSIM, PSNR, and MSE t...

Full description

Saved in:
Bibliographic Details
Main Authors: Changhyun Lee, Yunsik Kim, Hunkee Kim
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied System Innovation
Subjects:
Online Access:https://www.mdpi.com/2571-5577/7/6/127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850040998458032128
author Changhyun Lee
Yunsik Kim
Hunkee Kim
author_facet Changhyun Lee
Yunsik Kim
Hunkee Kim
author_sort Changhyun Lee
collection DOAJ
description In this study, we aimed to enhance the accuracy of product quality inspection and counting in the manufacturing process by integrating image processing and human body detection algorithms. We employed the SIFT algorithm combined with traditional image comparison metrics such as SSIM, PSNR, and MSE to develop a defect detection system that is robust against variations in rotation and scale. Additionally, the YOLOv8 Pose algorithm was used to detect and correct errors in product counting caused by human interference on the load cell in real time. By applying the image differencing technique, we accurately calculated the unit weight of products and determined their total count. In our experiments conducted on products weighing over 1 kg, we achieved a high accuracy of 99.268%. The integration of our algorithms with the load-cell-based counting system demonstrates reliable real-time quality inspection and automated counting in manufacturing environments.
format Article
id doaj-art-c9bfb6a1edbc4f959f40bdd89c74dd72
institution DOAJ
issn 2571-5577
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied System Innovation
spelling doaj-art-c9bfb6a1edbc4f959f40bdd89c74dd722025-08-20T02:55:54ZengMDPI AGApplied System Innovation2571-55772024-12-017612710.3390/asi7060127Computer-Vision-Based Product Quality Inspection and Novel Counting SystemChanghyun Lee0Yunsik Kim1Hunkee Kim2AI System Lab, Department of Advanced Materials Processing Engineering, Inha University, 36 Gaetbeol-ro, Yeonsu-gu, Incheon 21999, Republic of KoreaAI System Lab, Department of Advanced Materials Processing Engineering, Inha University, 36 Gaetbeol-ro, Yeonsu-gu, Incheon 21999, Republic of KoreaAI System Lab, Department of Advanced Materials Processing Engineering, Inha University, 36 Gaetbeol-ro, Yeonsu-gu, Incheon 21999, Republic of KoreaIn this study, we aimed to enhance the accuracy of product quality inspection and counting in the manufacturing process by integrating image processing and human body detection algorithms. We employed the SIFT algorithm combined with traditional image comparison metrics such as SSIM, PSNR, and MSE to develop a defect detection system that is robust against variations in rotation and scale. Additionally, the YOLOv8 Pose algorithm was used to detect and correct errors in product counting caused by human interference on the load cell in real time. By applying the image differencing technique, we accurately calculated the unit weight of products and determined their total count. In our experiments conducted on products weighing over 1 kg, we achieved a high accuracy of 99.268%. The integration of our algorithms with the load-cell-based counting system demonstrates reliable real-time quality inspection and automated counting in manufacturing environments.https://www.mdpi.com/2571-5577/7/6/127SIFT algorithmimage-based quality inspectionproduct countingYOLOv8 Poseload cellfeature matching
spellingShingle Changhyun Lee
Yunsik Kim
Hunkee Kim
Computer-Vision-Based Product Quality Inspection and Novel Counting System
Applied System Innovation
SIFT algorithm
image-based quality inspection
product counting
YOLOv8 Pose
load cell
feature matching
title Computer-Vision-Based Product Quality Inspection and Novel Counting System
title_full Computer-Vision-Based Product Quality Inspection and Novel Counting System
title_fullStr Computer-Vision-Based Product Quality Inspection and Novel Counting System
title_full_unstemmed Computer-Vision-Based Product Quality Inspection and Novel Counting System
title_short Computer-Vision-Based Product Quality Inspection and Novel Counting System
title_sort computer vision based product quality inspection and novel counting system
topic SIFT algorithm
image-based quality inspection
product counting
YOLOv8 Pose
load cell
feature matching
url https://www.mdpi.com/2571-5577/7/6/127
work_keys_str_mv AT changhyunlee computervisionbasedproductqualityinspectionandnovelcountingsystem
AT yunsikkim computervisionbasedproductqualityinspectionandnovelcountingsystem
AT hunkeekim computervisionbasedproductqualityinspectionandnovelcountingsystem