Published Patent: Method of inspecting images to detect defects
| Title | Method of inspecting images to detect defects |
| Granted Patent | 1148332 |
| Granted Date | 2005-11-30 |
| Priority Date | 2000-04-18 US 09/197708P |
| Inventors | KWOK-HUNG, GRANTHAM PANG, AIAY, KUMAR |
| Citation | EP Published Patent application EP 1148332. European Patent Office (EPO), Escapenet, 2005 |
| Abstract | The present invention relates to a method for automated defect detection in textured materials. The present invention utilizes linear Finite Impulse Response (FIR) filters with optimized energy separation. Specifically, the invention provides a method of inspecting industrial products for defects. The method has steps of: automated design of optimized filters from samples of products, using these optimal filters to filter the acquired images of product under inspection, computing the energy of each pixel in a local region, and finally segmenting the defect by thresholding each pixel. The present invention also relates to a method of inspection of unknown (unsupervised) defects in web materials. In an unsupervised inspection, information from a finite number of optimal filters is combined using a data fusion module.; This module attempts to nullify the false alarm associated with the information arriving from different channels. |
| DC Field | Value |
| dc.contributor.inventor | KWOK-HUNG, GRANTHAM PANG, |
|---|
| dc.contributor.inventor | AIAY, KUMAR |
|---|
| dc.date.accessioned | 2011-10-19T06:30:03Z |
|---|
| patents.date.application | 2001-04-18 |
|---|
| dc.date.available | 2011-10-19T06:30:03Z |
|---|
| patents.date.granted | 2005-11-30 |
|---|
| patents.date.priority | 2000-04-18 US 09/197708P |
|---|
| patents.date.publication | 2005-11-30 |
|---|
| dc.description.abstract | The present invention relates to a method for automated defect detection in textured materials. The present invention utilizes linear Finite Impulse Response (FIR) filters with optimized energy separation. Specifically, the invention provides a method of inspecting industrial products for defects. The method has steps of: automated design of optimized filters from samples of products, using these optimal filters to filter the acquired images of product under inspection, computing the energy of each pixel in a local region, and finally segmenting the defect by thresholding each pixel. The present invention also relates to a method of inspection of unknown (unsupervised) defects in web materials. In an unsupervised inspection, information from a finite number of optimal filters is combined using a data fusion module.; This module attempts to nullify the false alarm associated with the information arriving from different channels. |
|---|
| patents.description.assignee | UNIV HONG KONG [CN] |
|---|
| patents.description.cc | EP |
|---|
| patents.description.country | European Patent Office |
|---|
| patents.description.kind | B1 |
|---|
| patents.identifier.application | EP20010109375 |
|---|
| dc.identifier.citation | EP Published Patent application EP 1148332. European Patent Office (EPO), Escapenet, 2005 |
|---|
| patents.identifier.granted | 1148332 |
|---|
| patents.identifier.hkutechid | EEE-2000-00032 |
|---|
| patents.identifier.publication | EP 1148332 |
|---|
| dc.identifier.uri | http://hdl.handle.net/10722/142127 |
|---|
| patents.relation.family | CN 1335496 (A) 2002-02-13 |
|---|
| patents.relation.family | CN 100401043 (C) 2008-07-09 |
|---|
| patents.relation.family | DE 60115314 (T2) 2006-08-03 |
|---|
| patents.relation.family | HK 1042944 (A1) 2009-01-30 |
|---|
| patents.relation.family | US 2002054293 (A1) 2002-05-09 |
|---|
| patents.relation.family | US 6804381 (B2) 2004-10-12 |
|---|
| dc.relation.isreferencedby | AT 507939 (A1) 2010-09-15 |
|---|
| dc.relation.isreferencedby | AT 507939 (B1) 2012-02-15 |
|---|
| dc.rights | Creative Commons: Attribution 3.0 Hong Kong License For Public Patent Documents |
|---|
| dc.title | Method of inspecting images to detect defects |
|---|
| dc.type | Patent |
|---|
| patents.type | Patent_published |
|---|