Cover Image

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
http://eprints.usm.my/51673/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.usm.eprints.51673
record_format eprints
spelling my.usm.eprints.51673 http://eprints.usm.my/51673/ A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System 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 NonPeerReviewed application/pdf en http://eprints.usm.my/51673/1/WONG%20ZE-HAO%20-%20TESIS%20cut.pdf Wong, Ze-Hao (2020) A Reference Based Surface Defect Segmentation Algorithm For Automatic Optical Inspection System. PhD thesis, Universiti Sains Malaysia.
institution Universiti Sains Malaysia
building Hamzah Sendut Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Sains Malaysia
content_source USM Institutional Repository
url_provider http://eprints.usm.my/
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
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
publishDate 2020
url http://eprints.usm.my/51673/1/WONG%20ZE-HAO%20-%20TESIS%20cut.pdf
http://eprints.usm.my/51673/
_version_ 1725973346372288512
score 13.211869

Similar Items