Please use this identifier to cite or link to this item: http://nopr.niscair.res.in/handle/123456789/1369
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLin, Hong-Dar-
dc.contributor.authorLin, Gary C-
dc.contributor.authorChung, Chung-Yu-
dc.contributor.authorLin, Wan-Ting-
dc.date.accessioned2008-05-26T11:01:17Z-
dc.date.available2008-05-26T11:01:17Z-
dc.date.issued2008-06-
dc.identifier.issn0022-4456-
dc.identifier.urihttp://hdl.handle.net/123456789/1369-
dc.description412-420en_US
dc.description.abstractThis research explores automated visual inspection of surface defects in a light-emitting diode (LED) chip. One-level Haar wavelet transform is first used to decompose a chip image and extract four wavelet characteristics. Then, wavelet-based back-propagation network (WBPN) and wavelet-based Hotelling statistic (WHS) approaches are respectively applied to integrate multiple wavelet characteristics. Finally, back-propagation algorithm of WBPN or Hotelling test of WHS judges existence of defects. Two proposed methods achieve detection rates of above 90.8% and 92.4%, and false alarm rates below 4.4% and 6.1%, respectively. A valid computer-aided visual defect inspection system is contributed to help meet quality control needs of LED chip manufacturers.en_US
dc.language.isoen_USen_US
dc.publisherCSIRen_US
dc.sourceJSIR Vol.67(6) [June 2008]en_US
dc.subjectAutomated visual inspectionen_US
dc.subjectBack-propagation networken_US
dc.subjectHotelling statisticen_US
dc.subjectLED chip productionen_US
dc.subjectWavelet characteristicsen_US
dc.titleWavelet-based neural network and statistical approaches applied to automated visual inspection of LED chipsen_US
dc.typeArticleen_US
Appears in Collections: JSIR Vol.67(06) [June 2008]

Files in This Item:
File Description SizeFormat 
JSIR 67(6) (2008) 412-420.pdf238.92 kBAdobe PDFView/Open


Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.