The effect of different thresholding methods in RGB imaging

Jari Miettinen, Heikki Ailisto

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Typical surface inspection tasks using RGB vision require the analysis of tens of megabytes of image data per second, with low false alarm and error escape rates. Although automatic inspection systems have become more common on production lines, for example in sawmills, there are substantial needs to improve their performance and accuracy. Detection is one very important part of image flow before defect recognition. Detection is used in order to find suspicious regions of the image, containing possibly defective areas, since defect detection has to cope with very high data rates. It has to be based on relative simple methods. In this paper we describe the effect of different thresholding methods in RGB defect detection. Threshold values were calculated for R, G and B channels, difference channels |R-G|, |R-B| and |G-B| and for mean values from R, G and B channels. The analysis was performed for pine-wood. Error escape rate and false alarm rates were used as evaluation criteria. In this paper, R and G channel thresholding methods were the best ones.

Original languageEnglish
Title of host publicationIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision
PublisherInternational Society for Optics and Photonics SPIE
Pages459-465
Number of pages7
ISBN (Print)081944300X
DOIs
Publication statusPublished - 1 Dec 2001
MoE publication typeA4 Article in a conference publication
EventIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision - Boston, MA, United States
Duration: 29 Oct 200131 Oct 2001

Publication series

SeriesProceedings of SPIE
Volume4572
ISSN0277-786X

Conference

ConferenceIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision
CountryUnited States
CityBoston, MA
Period29/10/0131/10/01

Fingerprint

Inspection
Sawmills
Imaging techniques
false alarms
escape
inspection
Wood
defects
Defects
warning systems
thresholds
Defect detection
evaluation

Keywords

  • Color
  • Detection
  • Machine vision
  • Threshold
  • Wood

Cite this

Miettinen, J., & Ailisto, H. (2001). The effect of different thresholding methods in RGB imaging. In Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision (pp. 459-465). International Society for Optics and Photonics SPIE. Proceedings of SPIE, Vol.. 4572 https://doi.org/10.1117/12.444215
Miettinen, Jari ; Ailisto, Heikki. / The effect of different thresholding methods in RGB imaging. Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, 2001. pp. 459-465 (Proceedings of SPIE, Vol. 4572).
@inproceedings{ddc5e147614942f8ba2fed5329e8b04e,
title = "The effect of different thresholding methods in RGB imaging",
abstract = "Typical surface inspection tasks using RGB vision require the analysis of tens of megabytes of image data per second, with low false alarm and error escape rates. Although automatic inspection systems have become more common on production lines, for example in sawmills, there are substantial needs to improve their performance and accuracy. Detection is one very important part of image flow before defect recognition. Detection is used in order to find suspicious regions of the image, containing possibly defective areas, since defect detection has to cope with very high data rates. It has to be based on relative simple methods. In this paper we describe the effect of different thresholding methods in RGB defect detection. Threshold values were calculated for R, G and B channels, difference channels |R-G|, |R-B| and |G-B| and for mean values from R, G and B channels. The analysis was performed for pine-wood. Error escape rate and false alarm rates were used as evaluation criteria. In this paper, R and G channel thresholding methods were the best ones.",
keywords = "Color, Detection, Machine vision, Threshold, Wood",
author = "Jari Miettinen and Heikki Ailisto",
year = "2001",
month = "12",
day = "1",
doi = "10.1117/12.444215",
language = "English",
isbn = "081944300X",
series = "Proceedings of SPIE",
publisher = "International Society for Optics and Photonics SPIE",
pages = "459--465",
booktitle = "Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision",
address = "United States",

}

Miettinen, J & Ailisto, H 2001, The effect of different thresholding methods in RGB imaging. in Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, Proceedings of SPIE, vol. 4572, pp. 459-465, Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, Boston, MA, United States, 29/10/01. https://doi.org/10.1117/12.444215

The effect of different thresholding methods in RGB imaging. / Miettinen, Jari; Ailisto, Heikki.

Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE, 2001. p. 459-465 (Proceedings of SPIE, Vol. 4572).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - The effect of different thresholding methods in RGB imaging

AU - Miettinen, Jari

AU - Ailisto, Heikki

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Typical surface inspection tasks using RGB vision require the analysis of tens of megabytes of image data per second, with low false alarm and error escape rates. Although automatic inspection systems have become more common on production lines, for example in sawmills, there are substantial needs to improve their performance and accuracy. Detection is one very important part of image flow before defect recognition. Detection is used in order to find suspicious regions of the image, containing possibly defective areas, since defect detection has to cope with very high data rates. It has to be based on relative simple methods. In this paper we describe the effect of different thresholding methods in RGB defect detection. Threshold values were calculated for R, G and B channels, difference channels |R-G|, |R-B| and |G-B| and for mean values from R, G and B channels. The analysis was performed for pine-wood. Error escape rate and false alarm rates were used as evaluation criteria. In this paper, R and G channel thresholding methods were the best ones.

AB - Typical surface inspection tasks using RGB vision require the analysis of tens of megabytes of image data per second, with low false alarm and error escape rates. Although automatic inspection systems have become more common on production lines, for example in sawmills, there are substantial needs to improve their performance and accuracy. Detection is one very important part of image flow before defect recognition. Detection is used in order to find suspicious regions of the image, containing possibly defective areas, since defect detection has to cope with very high data rates. It has to be based on relative simple methods. In this paper we describe the effect of different thresholding methods in RGB defect detection. Threshold values were calculated for R, G and B channels, difference channels |R-G|, |R-B| and |G-B| and for mean values from R, G and B channels. The analysis was performed for pine-wood. Error escape rate and false alarm rates were used as evaluation criteria. In this paper, R and G channel thresholding methods were the best ones.

KW - Color

KW - Detection

KW - Machine vision

KW - Threshold

KW - Wood

UR - http://www.scopus.com/inward/record.url?scp=0035764189&partnerID=8YFLogxK

U2 - 10.1117/12.444215

DO - 10.1117/12.444215

M3 - Conference article in proceedings

AN - SCOPUS:0035764189

SN - 081944300X

T3 - Proceedings of SPIE

SP - 459

EP - 465

BT - Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision

PB - International Society for Optics and Photonics SPIE

ER -

Miettinen J, Ailisto H. The effect of different thresholding methods in RGB imaging. In Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision. International Society for Optics and Photonics SPIE. 2001. p. 459-465. (Proceedings of SPIE, Vol. 4572). https://doi.org/10.1117/12.444215