Tire Bubble Defects Detection Using ResNet
碩士 === 國立雲林科技大學 === 資訊工程系 === 107 === Digital shearography used to detect tire bubble defects that are unobservable by the naked-eye. The tire manufacturer obtains the tire image through digital shearography, and then judges the bubble defect through the experience operate. The determination of the...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/ph97y5 |
id |
ndltd-TW-107YUNT0392035 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107YUNT03920352019-09-03T03:43:16Z http://ndltd.ncl.edu.tw/handle/ph97y5 Tire Bubble Defects Detection Using ResNet 應用ResNet於輪胎氣泡缺陷檢測 WANG, FU-CHING 王富慶 碩士 國立雲林科技大學 資訊工程系 107 Digital shearography used to detect tire bubble defects that are unobservable by the naked-eye. The tire manufacturer obtains the tire image through digital shearography, and then judges the bubble defect through the experience operate. The determination of the bubble defects depends not only on the experience and observation of the personnel, but also because there is no uniform judgment standard due to different personnel. This thesis proposes a residual network to detect bubble defects. In the training phase, the whole tire image is divided into several blocks. Use the data augmentation method to increase the training sample, and then input into the network for training;In the test phase, the tire image is pre-processed to select suspected bubble defect areas, and then these suspicious areas are input into the network model for bubble defect classification. The final output is in two categories: bubble-defect and non-defect. In the experimental results, the bubble defect detection rate is about 95%, and the non-defect classification accuracy rate is about 85%. For this method which can help tire manufacturers to further achieve automated inspection and save labor costs. CHANG, CHUAN-YU 張傳育 2019 學位論文 ; thesis 57 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立雲林科技大學 === 資訊工程系 === 107 === Digital shearography used to detect tire bubble defects that are unobservable by the naked-eye. The tire manufacturer obtains the tire image through digital shearography, and then judges the bubble defect through the experience operate. The determination of the bubble defects depends not only on the experience and observation of the personnel, but also because there is no uniform judgment standard due to different personnel. This thesis proposes a residual network to detect bubble defects. In the training phase, the whole tire image is divided into several blocks. Use the data augmentation method to increase the training sample, and then input into the network for training;In the test phase, the tire image is pre-processed to select suspected bubble defect areas, and then these suspicious areas are input into the network model for bubble defect classification. The final output is in two categories: bubble-defect and non-defect. In the experimental results, the bubble defect detection rate is about 95%, and the non-defect classification accuracy rate is about 85%. For this method which can help tire manufacturers to further achieve automated inspection and save labor costs.
|
author2 |
CHANG, CHUAN-YU |
author_facet |
CHANG, CHUAN-YU WANG, FU-CHING 王富慶 |
author |
WANG, FU-CHING 王富慶 |
spellingShingle |
WANG, FU-CHING 王富慶 Tire Bubble Defects Detection Using ResNet |
author_sort |
WANG, FU-CHING |
title |
Tire Bubble Defects Detection Using ResNet |
title_short |
Tire Bubble Defects Detection Using ResNet |
title_full |
Tire Bubble Defects Detection Using ResNet |
title_fullStr |
Tire Bubble Defects Detection Using ResNet |
title_full_unstemmed |
Tire Bubble Defects Detection Using ResNet |
title_sort |
tire bubble defects detection using resnet |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/ph97y5 |
work_keys_str_mv |
AT wangfuching tirebubbledefectsdetectionusingresnet AT wángfùqìng tirebubbledefectsdetectionusingresnet AT wangfuching yīngyòngresnetyúlúntāiqìpàoquēxiànjiǎncè AT wángfùqìng yīngyòngresnetyúlúntāiqìpàoquēxiànjiǎncè |
_version_ |
1719242612916879360 |