Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection

Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection

碩士 === 國立雲林科技大學 === 資訊工程研究所 === 95 === Automatic visual inspection of defects plays an important role in industrial manufacturing with the benefits of low-cost and high accuracy. In light-emitting diode (LED) manufacturing, each die on the LED wafer must be inspected to determine whether it has defe...

Full description

Bibliographic Details
Main Authors: Chin-Huang Chang, 張金璜
Other Authors: Chuan-Yu Chang
Format: Others
Language:zh-TW
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/47582348564411150125
id ndltd-TW-095YUNT5392016
record_format oai_dc
spelling ndltd-TW-095YUNT53920162016-05-20T04:18:00Z http://ndltd.ncl.edu.tw/handle/47582348564411150125 Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection 學習向量量化類神經網路應用於發光二極體晶圓缺陷檢測 Chin-Huang Chang 張金璜 碩士 國立雲林科技大學 資訊工程研究所 95 Automatic visual inspection of defects plays an important role in industrial manufacturing with the benefits of low-cost and high accuracy. In light-emitting diode (LED) manufacturing, each die on the LED wafer must be inspected to determine whether it has defects or not. Therefore, detection of defective regions is a significant issue to discuss. In this paper, a new approach for inspection of LED wafer defects using the Learning Vector Quantization (LVQ) neural network is presented. In the wafer image, each die image can be taken and each of the regions of interest (ROI) can be handled separately. Then, by analyzing the properties of every ROI, we can extract specific geometric features and texture features. Using these features, the presented LVQ neural network is used to classify these dies as either acceptable or not. The experimental results confirm the effectiveness of the approach for LED wafer defect inspection. Chuan-Yu Chang 張傳育 2007 學位論文 ; thesis 78 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立雲林科技大學 === 資訊工程研究所 === 95 === Automatic visual inspection of defects plays an important role in industrial manufacturing with the benefits of low-cost and high accuracy. In light-emitting diode (LED) manufacturing, each die on the LED wafer must be inspected to determine whether it has defects or not. Therefore, detection of defective regions is a significant issue to discuss. In this paper, a new approach for inspection of LED wafer defects using the Learning Vector Quantization (LVQ) neural network is presented. In the wafer image, each die image can be taken and each of the regions of interest (ROI) can be handled separately. Then, by analyzing the properties of every ROI, we can extract specific geometric features and texture features. Using these features, the presented LVQ neural network is used to classify these dies as either acceptable or not. The experimental results confirm the effectiveness of the approach for LED wafer defect inspection.
author2 Chuan-Yu Chang
author_facet Chuan-Yu Chang
Chin-Huang Chang
張金璜
author Chin-Huang Chang
張金璜
spellingShingle Chin-Huang Chang
張金璜
Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
author_sort Chin-Huang Chang
title Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
title_short Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
title_full Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
title_fullStr Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
title_full_unstemmed Learning Vector Quantization Neural Networks for LED Wafer Defect Inspection
title_sort learning vector quantization neural networks for led wafer defect inspection
publishDate 2007
url http://ndltd.ncl.edu.tw/handle/47582348564411150125
work_keys_str_mv AT chinhuangchang learningvectorquantizationneuralnetworksforledwaferdefectinspection
AT zhāngjīnhuáng learningvectorquantizationneuralnetworksforledwaferdefectinspection
AT chinhuangchang xuéxíxiàngliàngliànghuàlèishénjīngwǎnglùyīngyòngyúfāguāngèrjítǐjīngyuánquēxiànjiǎncè
AT zhāngjīnhuáng xuéxíxiàngliàngliànghuàlèishénjīngwǎnglùyīngyòngyúfāguāngèrjítǐjīngyuánquēxiànjiǎncè
_version_ 1718272929226031104

Similar Items