Data Augmentation Framework for Improved Classification in Object Detectors

Deep Learning techniques have been classified as a significant advancement for data-driven industries such as electrical machine manufacturing. It has been used successfully for quality inspection in various manufacturing cases, enabling automated product inspection. However, a massive bottleneck in...

Full description

Saved in:
Bibliographic Details
Main Authors: Ioan-Alexandru Herdea, Divya Tiwari, John Oyekan, Ashutosh Tiwari
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10876126/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850024185992052736
author Ioan-Alexandru Herdea
Divya Tiwari
John Oyekan
Ashutosh Tiwari
author_facet Ioan-Alexandru Herdea
Divya Tiwari
John Oyekan
Ashutosh Tiwari
author_sort Ioan-Alexandru Herdea
collection DOAJ
description Deep Learning techniques have been classified as a significant advancement for data-driven industries such as electrical machine manufacturing. It has been used successfully for quality inspection in various manufacturing cases, enabling automated product inspection. However, a massive bottleneck in deploying deep learning for quality inspection in manufacturing operations is the unavailability of training data required to develop an effective model. Data augmentation techniques offer a solution by increasing the size and diversity of the training dataset. In recent years, studies have shown an improvement in the performance of object detectors through image augmentation. However, there is a gap in knowledge regarding the choice of an image augmentation technique and the reasoning behind the choice. This study proposes a framework for choosing an appropriate augmentation method in various scenarios. It was achieved by investigating pixel-level transformations in the context of data augmentation to enhance the training performance of Quality Inspection (QI) models in scenarios with extremely limited data. Firstly, the effects of four pixel-level transformations on YOLOv7 and SSD real-time detectors are analysed. Secondly, the augmentation effect transferability across dissimilar datasets is discussed. Lastly, a framework is proposed for choosing the appropriate augmentation method in various scenarios. The results show that the proposed framework provides consistent results with an average improvement of up to 35% in meanAP and a reduction of 50% in the classification loss for the electrical wires dataset.
format Article
id doaj-art-18f1efc3fd7840ce852c6e5a80ab077a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-18f1efc3fd7840ce852c6e5a80ab077a2025-08-20T03:01:11ZengIEEEIEEE Access2169-35362025-01-0113284762849110.1109/ACCESS.2025.353945510876126Data Augmentation Framework for Improved Classification in Object DetectorsIoan-Alexandru Herdea0https://orcid.org/0009-0000-5097-8566Divya Tiwari1https://orcid.org/0000-0003-4546-5031John Oyekan2https://orcid.org/0000-0001-6578-9928Ashutosh Tiwari3https://orcid.org/0000-0002-6197-1519School of Mechanical, Aerospace and Civil Engineering, The University of Sheffield, Sheffield, U.K.School of Mechanical, Aerospace and Civil Engineering, The University of Sheffield, Sheffield, U.K.Department of Computer Science, University of York, York, U.K.School of Mechanical, Aerospace and Civil Engineering, The University of Sheffield, Sheffield, U.K.Deep Learning techniques have been classified as a significant advancement for data-driven industries such as electrical machine manufacturing. It has been used successfully for quality inspection in various manufacturing cases, enabling automated product inspection. However, a massive bottleneck in deploying deep learning for quality inspection in manufacturing operations is the unavailability of training data required to develop an effective model. Data augmentation techniques offer a solution by increasing the size and diversity of the training dataset. In recent years, studies have shown an improvement in the performance of object detectors through image augmentation. However, there is a gap in knowledge regarding the choice of an image augmentation technique and the reasoning behind the choice. This study proposes a framework for choosing an appropriate augmentation method in various scenarios. It was achieved by investigating pixel-level transformations in the context of data augmentation to enhance the training performance of Quality Inspection (QI) models in scenarios with extremely limited data. Firstly, the effects of four pixel-level transformations on YOLOv7 and SSD real-time detectors are analysed. Secondly, the augmentation effect transferability across dissimilar datasets is discussed. Lastly, a framework is proposed for choosing the appropriate augmentation method in various scenarios. The results show that the proposed framework provides consistent results with an average improvement of up to 35% in meanAP and a reduction of 50% in the classification loss for the electrical wires dataset.https://ieeexplore.ieee.org/document/10876126/Data augmentationdefectselectric machine manufacturingframeworkobject detectionSSD
spellingShingle Ioan-Alexandru Herdea
Divya Tiwari
John Oyekan
Ashutosh Tiwari
Data Augmentation Framework for Improved Classification in Object Detectors
IEEE Access
Data augmentation
defects
electric machine manufacturing
framework
object detection
SSD
title Data Augmentation Framework for Improved Classification in Object Detectors
title_full Data Augmentation Framework for Improved Classification in Object Detectors
title_fullStr Data Augmentation Framework for Improved Classification in Object Detectors
title_full_unstemmed Data Augmentation Framework for Improved Classification in Object Detectors
title_short Data Augmentation Framework for Improved Classification in Object Detectors
title_sort data augmentation framework for improved classification in object detectors
topic Data augmentation
defects
electric machine manufacturing
framework
object detection
SSD
url https://ieeexplore.ieee.org/document/10876126/
work_keys_str_mv AT ioanalexandruherdea dataaugmentationframeworkforimprovedclassificationinobjectdetectors
AT divyatiwari dataaugmentationframeworkforimprovedclassificationinobjectdetectors
AT johnoyekan dataaugmentationframeworkforimprovedclassificationinobjectdetectors
AT ashutoshtiwari dataaugmentationframeworkforimprovedclassificationinobjectdetectors