|
NISCAIR ONLINE PERIODICALS REPOSITORY (NOPR) >
NISCAIR PUBLICATIONS >
Research Journals >
Journal of Scientific and Industrial Research (JSIR) >
JSIR Vol.67 [2008] >
JSIR Vol.67(06) [June 2008] >
| Title: | Wavelet-based neural network and statistical approaches applied to automated visual inspection of LED chips |
| Authors: | Lin, Hong-Dar
Lin, Gary C
Chung, Chung-Yu
Lin, Wan-Ting |
| Keywords: | Automated visual inspection
Back-propagation network
Hotelling statistic
LED chip production
Wavelet characteristics |
| Issue Date: | Jun-2008 |
| Publisher: | CSIR |
| Abstract: | This 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. |
| Page(s): | 412-420 |
| ISSN: | 0022-4456 |
| Source: | JSIR Vol.67(06) [June 2008]
|
|
