Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Fast visual recognition of Scots pine boards using template matching
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Wood Science and Engineering.
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Wood Science and Engineering.
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Wood Science and Engineering.ORCID iD: 0000-0001-8404-7356
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.

Place, publisher, year, edition, pages
2015. Vol. 118, p. 85-91
National Category
Other Mechanical Engineering
Research subject
Wood Science and Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-4185DOI: 10.1016/j.compag.2015.08.026ISI: 000364603500010Scopus ID: 2-s2.0-84940976908Local ID: 2166b466-813b-40a2-b89a-f4ea58e190d1OAI: oai:DiVA.org:ltu-4185DiVA, id: diva2:977049
Note

Validerad; 2015; Nivå 2; 20150226 (erikjo)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2018-07-10Bibliographically approved
In thesis
1. Wood fingerprint recognition and detection of thin cracks
Open this publication in new window or tab >>Wood fingerprint recognition and detection of thin cracks
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:nbn:se:ltu:diva-65701 (URN)978-91-7583-967-7 (ISBN)978-91-7583-968-4 (ISBN)
Public defence
2017-10-20, Hörsal A, Skellefteå, 09:00 (English)
Opponent
Supervisors
Funder
EU, FP7, Seventh Framework Programme, 284573
Available from: 2017-09-19 Created: 2017-09-18 Last updated: 2021-04-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Johansson, ErikPahlberg, TobiasHagman, Olle

Search in DiVA

By author/editor
Johansson, ErikPahlberg, TobiasHagman, Olle
By organisation
Wood Science and Engineering
In the same journal
Computers and Electronics in Agriculture
Other Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 288 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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