A image-based quality inspection system for automated handling of wooden parts

Research output: Contribution to conferenceConference articleScientific

Abstract

In this paper, we present a system for real-time quality inspection of wooden parts. The quality inspection system was developed for classifying wooden parts in an application with automated robotic handling operations. An essential feature is the detection of different grain patterns from the part surface. The quality inspection consists of CMOS camera imaging, texture analysis of images, and feature-based classification for evaluating the surface quality. The features are extracted from blobs and the classification algorithm relies on support vector machines. Based on our test results, the reliability of the classification is at a sufficient level.
Original languageEnglish
Pages200-205
Publication statusPublished - 2012
MoE publication typeNot Eligible
Event2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201 - , Singapore
Duration: 19 Nov 201220 Nov 2012

Conference

Conference2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201
Abbreviated titleM3 2012
CountrySingapore
Period19/11/1220/11/12

Fingerprint

Inspection
Surface properties
Support vector machines
Robotics
Textures
Cameras
Imaging techniques

Keywords

  • machine vision
  • support vector machine
  • wood processing
  • manufacturing

Cite this

Koskinen, J., Vaarala, T., & Heikkilä, T. (2012). A image-based quality inspection system for automated handling of wooden parts. 200-205. Paper presented at 2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, Singapore.
Koskinen, Jukka ; Vaarala, Tapio ; Heikkilä, Tapio. / A image-based quality inspection system for automated handling of wooden parts. Paper presented at 2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, Singapore.
@conference{b1e2e172f7fe4910b4bf05d947c37fa5,
title = "A image-based quality inspection system for automated handling of wooden parts",
abstract = "In this paper, we present a system for real-time quality inspection of wooden parts. The quality inspection system was developed for classifying wooden parts in an application with automated robotic handling operations. An essential feature is the detection of different grain patterns from the part surface. The quality inspection consists of CMOS camera imaging, texture analysis of images, and feature-based classification for evaluating the surface quality. The features are extracted from blobs and the classification algorithm relies on support vector machines. Based on our test results, the reliability of the classification is at a sufficient level.",
keywords = "machine vision, support vector machine, wood processing, manufacturing",
author = "Jukka Koskinen and Tapio Vaarala and Tapio Heikkil{\"a}",
year = "2012",
language = "English",
pages = "200--205",
note = "2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, M3 2012 ; Conference date: 19-11-2012 Through 20-11-2012",

}

Koskinen, J, Vaarala, T & Heikkilä, T 2012, 'A image-based quality inspection system for automated handling of wooden parts' Paper presented at 2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, Singapore, 19/11/12 - 20/11/12, pp. 200-205.

A image-based quality inspection system for automated handling of wooden parts. / Koskinen, Jukka; Vaarala, Tapio; Heikkilä, Tapio.

2012. 200-205 Paper presented at 2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, Singapore.

Research output: Contribution to conferenceConference articleScientific

TY - CONF

T1 - A image-based quality inspection system for automated handling of wooden parts

AU - Koskinen, Jukka

AU - Vaarala, Tapio

AU - Heikkilä, Tapio

PY - 2012

Y1 - 2012

N2 - In this paper, we present a system for real-time quality inspection of wooden parts. The quality inspection system was developed for classifying wooden parts in an application with automated robotic handling operations. An essential feature is the detection of different grain patterns from the part surface. The quality inspection consists of CMOS camera imaging, texture analysis of images, and feature-based classification for evaluating the surface quality. The features are extracted from blobs and the classification algorithm relies on support vector machines. Based on our test results, the reliability of the classification is at a sufficient level.

AB - In this paper, we present a system for real-time quality inspection of wooden parts. The quality inspection system was developed for classifying wooden parts in an application with automated robotic handling operations. An essential feature is the detection of different grain patterns from the part surface. The quality inspection consists of CMOS camera imaging, texture analysis of images, and feature-based classification for evaluating the surface quality. The features are extracted from blobs and the classification algorithm relies on support vector machines. Based on our test results, the reliability of the classification is at a sufficient level.

KW - machine vision

KW - support vector machine

KW - wood processing

KW - manufacturing

M3 - Conference article

SP - 200

EP - 205

ER -

Koskinen J, Vaarala T, Heikkilä T. A image-based quality inspection system for automated handling of wooden parts. 2012. Paper presented at 2nd Annual International Conference on Materials Science, Metal & Manufacturing. M3 201, Singapore.