A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System

Surface defect segmentation algorithms in Automatic Optical Inspection (AOI) system for modern manufacturing industries provide solutions to quality control with speed, volume and traceability. However, present complex algorithms which are accurate require high processing power using a large size of...

Full description

Saved in:

Bibliographic Details
Main Author:	Wong, Ze-Hao
Format:	Thesis
Language:	English
Published:	2020
Subjects:	QC1-999 Physics
Online Access:	http://eprints.usm.my/51673/1/WONG%20ZE-HAO%20-%20TESIS%20cut.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-usm-ep.51673
record_format	uketd_dc
spelling	my-usm-ep.516732022-02-25T14:19:44Z A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System 2020-06 Wong, Ze-Hao QC1-999 Physics Surface defect segmentation algorithms in Automatic Optical Inspection (AOI) system for modern manufacturing industries provide solutions to quality control with speed, volume and traceability. However, present complex algorithms which are accurate require high processing power using a large size of learning dataset without labelling error. On the other hand, simple algorithms are not suitable for surfaces with complicated designs and variations. This study aims to develop an algorithm for the AOI system to segment and detect surface defects, requiring low processing power and a small number of learning dataset with labelling error resistance. Multiple Templates Anomaly Detection (MTAD) strategy is proposed to describe the local anomaly degree through distance functions computed from learning dataset. The learning dataset images are illumination normalized, registered and stacked across multiple templates in a kernel to form a histogram for each pixel location. Then, the histogram distance function for each location is computed using a pseudo-probability combination of novel histogram distance functions on a clustered histogram. Finally, surface defects are segmented from an anomaly heat map which is generated based on histogram distance functions. Results show that the proposed algorithm required a learning dataset size as small as 5 samples and was resistant to learning labelling error up to 50%. 2020-06 Thesis http://eprints.usm.my/51673/ http://eprints.usm.my/51673/1/WONG%20ZE-HAO%20-%20TESIS%20cut.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Fizik
institution	Universiti Sains Malaysia
collection	USM Institutional Repository
language	English
topic	QC1-999 Physics
spellingShingle	QC1-999 Physics Wong, Ze-Hao A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
description	Surface defect segmentation algorithms in Automatic Optical Inspection (AOI) system for modern manufacturing industries provide solutions to quality control with speed, volume and traceability. However, present complex algorithms which are accurate require high processing power using a large size of learning dataset without labelling error. On the other hand, simple algorithms are not suitable for surfaces with complicated designs and variations. This study aims to develop an algorithm for the AOI system to segment and detect surface defects, requiring low processing power and a small number of learning dataset with labelling error resistance. Multiple Templates Anomaly Detection (MTAD) strategy is proposed to describe the local anomaly degree through distance functions computed from learning dataset. The learning dataset images are illumination normalized, registered and stacked across multiple templates in a kernel to form a histogram for each pixel location. Then, the histogram distance function for each location is computed using a pseudo-probability combination of novel histogram distance functions on a clustered histogram. Finally, surface defects are segmented from an anomaly heat map which is generated based on histogram distance functions. Results show that the proposed algorithm required a learning dataset size as small as 5 samples and was resistant to learning labelling error up to 50%.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Wong, Ze-Hao
author_facet	Wong, Ze-Hao
author_sort	Wong, Ze-Hao
title	A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
title_short	A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
title_full	A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
title_fullStr	A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
title_full_unstemmed	A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System
title_sort	reference based surface defect segmentation algorithm for automatic optical inspection system
granting_institution	Universiti Sains Malaysia
granting_department	Pusat Pengajian Sains Fizik
publishDate	2020
url	http://eprints.usm.my/51673/1/WONG%20ZE-HAO%20-%20TESIS%20cut.pdf
_version_	1747822092934447104

A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System

Similar Items