| dc.contributor.author |
Bhandarkar, SM |
en |
| dc.contributor.author |
Luo, X |
en |
| dc.contributor.author |
Daniels, R |
en |
| dc.contributor.author |
Tollner, EW |
en |
| dc.date.accessioned |
2014-06-06T06:46:14Z |
|
| dc.date.available |
2014-06-06T06:46:14Z |
|
| dc.date.issued |
2005 |
en |
| dc.identifier.issn |
01678655 |
en |
| dc.identifier.uri |
http://dx.doi.org/10.1016/j.patrec.2005.04.004 |
en |
| dc.identifier.uri |
http://62.217.125.90/xmlui/handle/123456789/2856 |
|
| dc.subject |
Computer tomography |
en |
| dc.subject |
Crack detection |
en |
| dc.subject |
Internal defect detection |
en |
| dc.subject |
Internal log defects |
en |
| dc.subject |
Log scanning |
en |
| dc.subject |
Lumber production planning |
en |
| dc.subject.other |
Computerized tomography |
en |
| dc.subject.other |
Contour followers |
en |
| dc.subject.other |
Cracks |
en |
| dc.subject.other |
Lumber |
en |
| dc.subject.other |
Productivity |
en |
| dc.subject.other |
Sawing |
en |
| dc.subject.other |
Scanning |
en |
| dc.subject.other |
Computer tomography |
en |
| dc.subject.other |
Crack detection |
en |
| dc.subject.other |
Internal defect detection |
en |
| dc.subject.other |
Internal log defects |
en |
| dc.subject.other |
Log scanning |
en |
| dc.subject.other |
Lumber production planning |
en |
| dc.subject.other |
Image analysis |
en |
| dc.subject.other |
Cracks |
en |
| dc.subject.other |
Image Analysis |
en |
| dc.subject.other |
Logs |
en |
| dc.subject.other |
Lumber |
en |
| dc.subject.other |
Production |
en |
| dc.subject.other |
Sawing |
en |
| dc.subject.other |
Scanning |
en |
| dc.subject.other |
Shape |
en |
| dc.title |
Detection of cracks in computer tomography images of logs |
en |
| heal.type |
journalArticle |
en |
| heal.identifier.primary |
10.1016/j.patrec.2005.04.004 |
en |
| heal.publicationDate |
2005 |
en |
| heal.abstract |
Computer Tomography (CT) is being increasingly employed for automated detection and localization of internal defects in logs prior to their sawing. Reliable detection and localization of cracks in CT images of logs is particularly important from the viewpoint of lumber production planning since the presence of cracks substantially reduces the value and also compromises the structural strength of the resulting lumber. A crack is hard to detect in a cross-sectional CT image of a log because it has geometric properties and grayscale values that are similar to those associated with the ring structure of the log. In this paper, a method for crack detection is presented, which exploits the fact that the line defining the crack makes a significant non-zero angle with the log ring structure. Sobel-like operators are used to extract both, the line defining the crack and the contours corresponding to the grayscale valleys between two neighboring rings. Fork detection and grouping methods are subsequently employed to localize the actual crack line using a RANSAC-based line fitting procedure. Experimental results show the advantages of the proposed technique for crack detection when compared to techniques that employ straightforward grayscale histogram-based thresholding. © 2005 Elsevier B.V. All rights reserved. |
en |
| heal.journalName |
Pattern Recognition Letters |
en |
| dc.identifier.issue |
14 |
en |
| dc.identifier.volume |
26 |
en |
| dc.identifier.doi |
10.1016/j.patrec.2005.04.004 |
en |
| dc.identifier.spage |
2282 |
en |
| dc.identifier.epage |
2294 |
en |