Die defect classification using image processing
This work presents die defect classification using image processing. The detection of the flaw is based on the defect features in the die. Each unique defect or feature structure is defined from samples that has been collected by Visual Inspection Inspectors. The defects are then grouped into user d...
Saved in:
Main Author: | |
---|---|
Format: | Thesis |
Language: | English |
Published: |
2015
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/53921/1/DarmadevaindraManiamMFKE2015.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my-utm-ep.53921 |
---|---|
record_format |
uketd_dc |
spelling |
my-utm-ep.539212020-10-08T03:32:14Z Die defect classification using image processing 2015-06 Maniam, Darmadevaindra TK Electrical engineering. Electronics Nuclear engineering This work presents die defect classification using image processing. The detection of the flaw is based on the defect features in the die. Each unique defect or feature structure is defined from samples that has been collected by Visual Inspection Inspectors. The defects are then grouped into user definition categories such as blob, pin hole, underfill and die crack.This work also describes the image processing algorithms utilized to perform defect classification. The defect classification was developed from MATLAB program.It is aimed at locating the Region of Interest of the die from the image and extract it. The extracted image is then used to classify or recognize the specific classification category of the defect.Total samples that is being used in this project is 67 die samples. The results obtained from this work shows the overall accuracy of 94% for die defect detection and 87% for defect classification. 2015-06 Thesis http://eprints.utm.my/id/eprint/53921/ http://eprints.utm.my/id/eprint/53921/1/DarmadevaindraManiamMFKE2015.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:85629 masters Universiti Teknologi Malaysia, Faculty of Electrical Engineering Faculty of Electrical Engineering |
institution |
Universiti Teknologi Malaysia |
collection |
UTM Institutional Repository |
language |
English |
topic |
TK Electrical engineering Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering Electronics Nuclear engineering Maniam, Darmadevaindra Die defect classification using image processing |
description |
This work presents die defect classification using image processing. The detection of the flaw is based on the defect features in the die. Each unique defect or feature structure is defined from samples that has been collected by Visual Inspection Inspectors. The defects are then grouped into user definition categories such as blob, pin hole, underfill and die crack.This work also describes the image processing algorithms utilized to perform defect classification. The defect classification was developed from MATLAB program.It is aimed at locating the Region of Interest of the die from the image and extract it. The extracted image is then used to classify or recognize the specific classification category of the defect.Total samples that is being used in this project is 67 die samples. The results obtained from this work shows the overall accuracy of 94% for die defect detection and 87% for defect classification. |
format |
Thesis |
qualification_level |
Master's degree |
author |
Maniam, Darmadevaindra |
author_facet |
Maniam, Darmadevaindra |
author_sort |
Maniam, Darmadevaindra |
title |
Die defect classification using image processing |
title_short |
Die defect classification using image processing |
title_full |
Die defect classification using image processing |
title_fullStr |
Die defect classification using image processing |
title_full_unstemmed |
Die defect classification using image processing |
title_sort |
die defect classification using image processing |
granting_institution |
Universiti Teknologi Malaysia, Faculty of Electrical Engineering |
granting_department |
Faculty of Electrical Engineering |
publishDate |
2015 |
url |
http://eprints.utm.my/id/eprint/53921/1/DarmadevaindraManiamMFKE2015.pdf |
_version_ |
1747817658129055744 |