Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Wood fingerprint recognition and detection of thin cracks
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Wood Science and Engineering. Luleå University of Technology.
2017 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The first part of this thesis deals with recognition of wood fingerprints extracted from timber surfaces. It presents different methods to track sawn wood products through an industrial process using cameras. The possibility of identifying individual wood products comes from the biological variation of trees, where the genetic code, environment, and breakdown process means that every board has a unique appearance. Wood fingerprint recognition experiences many of the same challenges as found in human biometrics applications. 

The vision for the future is to be able to utilize existing imaging sensors in the production line to track individual products through a disordered and diverging product flow. The flow speed in wood industries is usually very high, 2-15 meters per second, with a high degree of automation. Wood fingerprints combined with automated inspection makes it possible to tailor subsequent processing steps for each product and can be used to deliver customized products. Wood tracking can also give the machine operators vital feedback on the process parameters. 

The motivation for recognition comes from the need for the wood industry to keep track of products without using invasive methods, such as bar code stickers or painted labels. In the project Hol-i-Wood Patching Robot, an automatic scanner- and robot system was developed. In this project, there was a wish to keep track of the shuttering panels that were going to be repaired by the automatic robots. 

In this thesis, three different strategies to recognize previously scanned sawn wood products are presented. The first approach uses feature detectors to find matching features between two images. This approach proved to be robust, even when subjected to moderate geometric- and radiometric image distortions. The recognition accuracy reached 100% when using high quality scans of Scots pine boards that had more than 20 knots. 

The second approach uses local knot neighborhood geometry to find point matches between images. The recognition accuracy reached above 99% when matching simulated Scots pine panels with realistically added noise to the knot positions, given the assumption that 85% of the knots could be detected.

The third approach uses template matching to match a small part of a board against a large set of full-length boards. Cropping and heavy downsampling was implemented in this study. The intensity normalized algorithms using cross-correlation (CC-N) and correlation coefficient (CCF-N) obtained the highest recognition accuracy and had very similar overall performance. For instance, the matching accuracy for the CCF-N method reached above 99% for query images of length 1 m when the pixel density was above 0.08 pixels/mm.

The last part of this thesis deals with the detection of thin cracks on oak flooring lamellae using ultrasound-excited thermography and machine learning. Today, many people manually grade and detect defects on wooden lamellae in the parquet flooring industry. The last appended paper investigates the possibility to use ensemble methods random forests and boosting to automate the process. When friction occurs in thin cracks they become warm and thus visible for a thermographic camera. Several image processing techniques were used to suppress noise and enhance likely cracks in the images. The best ensemble methods reached an average classification accuracy of 0.8, which was very close to the authors own manual attempt at separating the images (0.83).

Place, publisher, year, edition, pages
Luleå: Luleå University of Technology, 2017. , p. 168
Series
Doctoral thesis / Luleå University of Technology 1 jan 1997 → …, ISSN 1402-1544
National Category
Wood Science
Research subject
Wood Science and Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-65701ISBN: 978-91-7583-967-7 (print)ISBN: 978-91-7583-968-4 (electronic)OAI: oai:DiVA.org:ltu-65701DiVA, id: diva2:1142035
Public defence
2017-10-20, Hörsal A, Skellefteå, 09:00 (English)
Opponent
Supervisors
Funder
EU, FP7, Seventh Framework Programme, 284573Available from: 2017-09-19 Created: 2017-09-18 Last updated: 2017-11-24Bibliographically approved
List of papers
1. Crack detection in oak flooring lamellae using ultrasound-excited thermography
Open this publication in new window or tab >>Crack detection in oak flooring lamellae using ultrasound-excited thermography
2018 (English)In: Infrared physics & technology, ISSN 1350-4495, E-ISSN 1879-0275, Vol. 88, p. 57-69Article in journal (Refereed) Published
Abstract [en]

Today, a large number of people are manually grading and detecting defects in wooden lamellae in the parquet flooring industry. This paper investigates the possibility of using the ensemble methods random forests and boosting to automatically detect cracks using ultrasound-excited thermography and a variety of predictor variables. When friction occurs in thin cracks, they become warm and thus visible to a thermographic camera. Several image processing techniques have been used to suppress the noise and enhance probable cracks in the images. The most successful predictor variables captured the upper part of the heat distribution, such as the maximum temperature, kurtosis and percentile values 92–100 of the edge pixels. The texture in the images was captured by Completed Local Binary Pattern histograms and cracks were also segmented by background suppression and thresholding.

The classification accuracy was significantly improved from previous research through added image processing, introduction of more predictors, and by using automated machine learning. The best ensemble methods reach an average classification accuracy of 0.8, which is very close to the authors’ own manual attempt at separating the images (0.83).

Place, publisher, year, edition, pages
Elsevier, 2018
National Category
Computer Vision and Robotics (Autonomous Systems) Other Mechanical Engineering Signal Processing
Research subject
Wood Science and Engineering; Signal Processing
Identifiers
urn:nbn:se:ltu:diva-65698 (URN)10.1016/j.infrared.2017.11.007 (DOI)000423650700007 ()2-s2.0-85034628056 (Scopus ID)
Note

Validerad;2017;Nivå 2;2017-12-05 (andbra)

Available from: 2017-09-18 Created: 2017-09-18 Last updated: 2018-02-16Bibliographically approved
2. Wood fingerprint recognition using knot neighborhood K-plet descriptors
Open this publication in new window or tab >>Wood fingerprint recognition using knot neighborhood K-plet descriptors
2015 (English)In: Wood Science and Technology, ISSN 0043-7719, E-ISSN 1432-5225, Vol. 49, no 1, p. 7-20Article in journal (Refereed) Published
Abstract [en]

In the wood industry, there is a wish to recognize and track wood products through production chains. Traceability would facilitate improved process control and extraction of quality measures of various production steps. In this paper, a novel wood surface recognition system that uses scale and rotationally invariant feature descriptors called K-plets is described and evaluated. The idea behind these descriptors is to use information of how knots are positioned in relation to each other. The performance and robustness of the proposed system were tested on 212 wood panel images with varying levels of normally distributed errors applied to the knot positions. The results showed that the proposed method is able to successfully identify 99–100 % of all panel images with knot positional error levels that can be expected in practical applications

National Category
Other Mechanical Engineering Signal Processing
Research subject
Signal Processing; Wood Science and Engineering
Identifiers
urn:nbn:se:ltu:diva-7733 (URN)10.1007/s00226-014-0679-3 (DOI)000347166900002 ()2-s2.0-84938410671 (Scopus ID)6266a684-7c00-49d2-ac80-b65cd350c889 (Local ID)6266a684-7c00-49d2-ac80-b65cd350c889 (Archive number)6266a684-7c00-49d2-ac80-b65cd350c889 (OAI)
Note

Validerad; 2015; Nivå 2; 20140429 (erikjo)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
3. Recognition of boards using wood fingerprints based on a fusion of feature detection methods
Open this publication in new window or tab >>Recognition of boards using wood fingerprints based on a fusion of feature detection methods
2015 (English)In: Computers and Electronics in Agriculture, ISSN 0168-1699, E-ISSN 1872-7107, Vol. 111, p. 164-173Article in journal (Refereed) Published
Abstract [en]

This paper investigates the possibility to automatically match and recognize individual Scots pine (Pinus sylvestris L.) boards using a fusion of two feature detection methods. The first method denoted Block matching method, detects corners and matches square regions around these corners using a normalized Sum of Squared Differences (SSD) measure. The second method denoted the SURF (Speeded-Up Robust Features) matching method, matches SURF features between images (Bay et al., 2008). The fusion of the two feature detection methods improved the recognition rate of wooden floorboards substantially compared to the individual methods. Perfect matching accuracy was obtained for board pieces with more than 20 knots using high quality images. More than 90% matching accuracy was achieved for board pieces with more than 10 knots, using both high- and low quality images.

National Category
Other Mechanical Engineering Signal Processing
Research subject
Signal Processing; Wood Science and Engineering
Identifiers
urn:nbn:se:ltu:diva-3568 (URN)10.1016/j.compag.2014.12.014 (DOI)000350942800020 ()2-s2.0-84921515668 (Scopus ID)16587b6c-231a-417c-a13c-834c3944a9f3 (Local ID)16587b6c-231a-417c-a13c-834c3944a9f3 (Archive number)16587b6c-231a-417c-a13c-834c3944a9f3 (OAI)
Note

Validerad; 2015; Nivå 2; 20150122 (tobpah)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
4. Feature recognition and fingerprint sensing for guiding a wood patching robot
Open this publication in new window or tab >>Feature recognition and fingerprint sensing for guiding a wood patching robot
2012 (English)In: World Conference on Timber Engineering: WCTE Auckland New Zealand 15-19 July 2012 / [ed] Pierre Quenneville, Auckland: New Zealand Timber Design Society , 2012, p. 724-733Conference paper, Published paper (Other academic)
Abstract [en]

This paper includes a summary of a few commonly used object recognition techniques, as well as a sensitivity analysis of two feature point recognition methods. The robustness was analyzed by automatically trying to recognize 886 images of pine floorboards after applying different levels of distortions. Recognition was also tested on a subset of 5% of the boards which were both re-scanned using a line scan camera and photographed using a digital camera. Experiments showed that both the Block matching method and the SURF method are valid options for recognizing wood products covered with distinct features. The Block matching method outperformed the SURF method for small geometric distortions and moderate radiometric distortions. The SURF method, in its turn, performed better compared to the other method when faced with low resolution digital images.

Place, publisher, year, edition, pages
Auckland: New Zealand Timber Design Society, 2012
Keywords
Information technology - Computer science, Image analysis, Classification, Feature recognition, Fingerprint, Sensor fusion, Holonic, Patching robot, Wood, Hol-i-Wood PR, Informationsteknik - Datorvetenskap
National Category
Other Mechanical Engineering
Research subject
Wood Products Engineering
Identifiers
urn:nbn:se:ltu:diva-35703 (URN)a5a89059-d44a-43d5-95fd-13de2346604b (Local ID)9781622763054 (ISBN)a5a89059-d44a-43d5-95fd-13de2346604b (Archive number)a5a89059-d44a-43d5-95fd-13de2346604b (OAI)
Conference
World Conference on Timber Engineering : 15/07/2012 - 19/07/2012
Projects
Holonic Integration of Cognition, Communication and Control for a Wood Patching Robot
Note
Godkänd; 2012; 20120816 (tobpah)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2017-11-25Bibliographically approved
5. Fast visual recognition of Scots pine boards using template matching
Open this publication in new window or tab >>Fast visual recognition of Scots pine boards using template matching
2015 (English)In: Computers and Electronics in Agriculture, ISSN 0168-1699, E-ISSN 1872-7107, Vol. 118, p. 85-91Article in journal (Refereed) Published
Abstract [en]

This paper describes how the image processing technique known as template matching performs when used to recognize boards of Scots pine (Pinus sylvestris L.). Recognition of boards enables tracking of individual boards through an industrial process, which is vital for process optimization.A dataset of 886 Scots pine board images were used as a database to match against. The proposed board recognition method was evaluated by rescanning 44 of the boards and matching these to the larger dataset. Three different template matching algorithms have been investigated while reducing the pixel densities of the board images (downsampling the images). Furthermore, the effect of variations in board length has been tested and the computational speed of the recognition with respect to the database size has been measured. Tests were conducted using the open source software package OpenCV due to its highly optimized code which is essential for applications with high production speed.The conducted tests resulted in recognition rates above 99% for board lengths down to 1 m and pixel densities down to 0.06 pixels/mm. This study concluded that template matching is a good choice for recognition of wooden board surfaces.

National Category
Other Mechanical Engineering
Research subject
Wood Science and Engineering
Identifiers
urn:nbn:se:ltu:diva-4185 (URN)10.1016/j.compag.2015.08.026 (DOI)000364603500010 ()2-s2.0-84940976908 (Scopus ID)2166b466-813b-40a2-b89a-f4ea58e190d1 (Local ID)2166b466-813b-40a2-b89a-f4ea58e190d1 (Archive number)2166b466-813b-40a2-b89a-f4ea58e190d1 (OAI)
Note

Validerad; 2015; Nivå 2; 20150226 (erikjo)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved

Open Access in DiVA

fulltext(101034 kB)97 downloads
File information
File name FULLTEXT02.pdfFile size 101034 kBChecksum SHA-512
790172325e249025f5ecfece1650a178134cd1b9b85046324c2528bae11bf5ff84675fd5fb01febf17e536c435ef9044a41099991acf7f2e2396fb31440f86f1
Type fulltextMimetype application/pdf
errata(99 kB)11 downloads
File information
File name ERRATA01.pdfFile size 99 kBChecksum SHA-512
5463efb1f8076d19f4d172256238e71521686482e7b208729ff0d78727f1f19f78b82b1caa7bb782f9e45274637b88e49a12616509aed5392dce3c3e79b295b5
Type errataMimetype application/pdf

Authority records BETA

Pahlberg, Tobias

Search in DiVA

By author/editor
Pahlberg, Tobias
By organisation
Wood Science and Engineering
Wood Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 97 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 547 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf