DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses

Vision-based inspection systems are essential for quality control in manufacturing industries, and advances in artificial intelligence (AI) have significantly enhanced their accuracy. However, the high-precision requirements of products such as contact lenses demand even more robust inspection metho...

Full description

Saved in:
Bibliographic Details
Main Authors: Sung-Hoon Kim, Seong-Jong Joo, Kwan-Hee Yoo
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2697
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053229507772416
author Sung-Hoon Kim
Seong-Jong Joo
Kwan-Hee Yoo
author_facet Sung-Hoon Kim
Seong-Jong Joo
Kwan-Hee Yoo
author_sort Sung-Hoon Kim
collection DOAJ
description Vision-based inspection systems are essential for quality control in manufacturing industries, and advances in artificial intelligence (AI) have significantly enhanced their accuracy. However, the high-precision requirements of products such as contact lenses demand even more robust inspection methods. This paper introduces a novel defect-adaptive hierarchical structure convolution neural network (DHS-CNN) model based on InceptionV4. The proposed model architecture reflects the manufacturing process and defect types, and we developed a custom loss function to suit this multi-output hierarchical design. Experimental results on a dataset of 2800 contact lens images revealed that the proposed model improved accuracy by 2.08% over the baseline model. These findings suggest that the defect-adaptive hierarchical structure and customized loss function offer substantial improvements in the vision-based inspection of contact lenses and may enhance AI-driven quality control processes in other manufacturing sectors.
format Article
id doaj-art-c948d77bff38401db16a8205996bb2a2
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c948d77bff38401db16a8205996bb2a22025-08-20T02:52:35ZengMDPI AGApplied Sciences2076-34172025-03-01155269710.3390/app15052697DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact LensesSung-Hoon Kim0Seong-Jong Joo1Kwan-Hee Yoo2Department of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, Republic of KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, Republic of KoreaDepartment of Computer Science, Chungbuk National University, Chungdae-ro 1, Seowon-Gu, Cheongju 28644, Republic of KoreaVision-based inspection systems are essential for quality control in manufacturing industries, and advances in artificial intelligence (AI) have significantly enhanced their accuracy. However, the high-precision requirements of products such as contact lenses demand even more robust inspection methods. This paper introduces a novel defect-adaptive hierarchical structure convolution neural network (DHS-CNN) model based on InceptionV4. The proposed model architecture reflects the manufacturing process and defect types, and we developed a custom loss function to suit this multi-output hierarchical design. Experimental results on a dataset of 2800 contact lens images revealed that the proposed model improved accuracy by 2.08% over the baseline model. These findings suggest that the defect-adaptive hierarchical structure and customized loss function offer substantial improvements in the vision-based inspection of contact lenses and may enhance AI-driven quality control processes in other manufacturing sectors.https://www.mdpi.com/2076-3417/15/5/2697vision inspection in manufacturingautomated optical inspectiondeep learningartificial intelligencedefect-adapted hierarchical structuremulti-output
spellingShingle Sung-Hoon Kim
Seong-Jong Joo
Kwan-Hee Yoo
DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
Applied Sciences
vision inspection in manufacturing
automated optical inspection
deep learning
artificial intelligence
defect-adapted hierarchical structure
multi-output
title DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
title_full DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
title_fullStr DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
title_full_unstemmed DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
title_short DHS-CNN: A Defect-Adaptive Hierarchical Structure CNN Model for Detecting Anomalies in Contact Lenses
title_sort dhs cnn a defect adaptive hierarchical structure cnn model for detecting anomalies in contact lenses
topic vision inspection in manufacturing
automated optical inspection
deep learning
artificial intelligence
defect-adapted hierarchical structure
multi-output
url https://www.mdpi.com/2076-3417/15/5/2697
work_keys_str_mv AT sunghoonkim dhscnnadefectadaptivehierarchicalstructurecnnmodelfordetectinganomaliesincontactlenses
AT seongjongjoo dhscnnadefectadaptivehierarchicalstructurecnnmodelfordetectinganomaliesincontactlenses
AT kwanheeyoo dhscnnadefectadaptivehierarchicalstructurecnnmodelfordetectinganomaliesincontactlenses