Comparison on eggplant fruit grading between nir-color camera and color camera

V. K. Chong, N. Kondo, K. Ninomiya, Mitsuji Monta, Kazuhiko Namba

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

An eggplant grading system was introduced in a JA (agricultural cooperative association) at Okayama, 2002. 6 CCD color cameras were installed to evaluate fruit appearance (fruit color, size, shape, bruise, and diseases), before and after turning over in a line and connected to 2 PCs through 6 image grabber boards, Physical properties of the fruits such as fruit length, average, maximum, and minimum diameters, area, apparent volume, fruit color, calyx color, fruit shape, degree of fruit bend, bruise number, bruise area, and so on were extracted from the images. The 6 CCD color cameras were divided into 2 units, which consisted of 3 cameras each set, were installed for complete surface inspection. However it is not easy to detect several kinds of defects on eggplant fruit surface because the fruit has very dark purple color and several defects are very similar colors with normal skin. In this paper, a new color camera whose sensitivity ranges from visible region to infrared region was used. Most of the fruits have higher spectral reflectance in infrared region (700-1200nm). The color CCD camera had the same G and B components with usual color camera, but R signal includes infrared region was specially ordered. Although a color balance among R, G, and B is lost, it was considered that slight color changes of defects and discrimination from dark background were easier than the usual color CCD camera. HSI and chromaticity conversions were tested as a preprocessing to detect various defects. With the improvement on the detections of bruises and defects, this will further increase the effectiveness of the current eggplant-grading machine.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004
EditorsQ. Zhang, M. Iida, A. Mizushima
Pages387-393
Number of pages7
Publication statusPublished - 2004
EventInternational Conference on Automation Technology for Off-road Equipment, ATOE 2004 - Kyoto, Japan
Duration: Oct 7 2004Oct 8 2004

Other

OtherInternational Conference on Automation Technology for Off-road Equipment, ATOE 2004
CountryJapan
CityKyoto
Period10/7/0410/8/04

Fingerprint

Fruits
Cameras
Color
Defects
CCD cameras
Infrared radiation
Charge coupled devices
Skin
Physical properties
Inspection

Keywords

  • Eggplant
  • Grading
  • Machine vision
  • Quality evaluation
  • Spectral reflectance
  • TV camera

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chong, V. K., Kondo, N., Ninomiya, K., Monta, M., & Namba, K. (2004). Comparison on eggplant fruit grading between nir-color camera and color camera. In Q. Zhang, M. Iida, & A. Mizushima (Eds.), Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004 (pp. 387-393). [11B]

Comparison on eggplant fruit grading between nir-color camera and color camera. / Chong, V. K.; Kondo, N.; Ninomiya, K.; Monta, Mitsuji; Namba, Kazuhiko.

Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004. ed. / Q. Zhang; M. Iida; A. Mizushima. 2004. p. 387-393 11B.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chong, VK, Kondo, N, Ninomiya, K, Monta, M & Namba, K 2004, Comparison on eggplant fruit grading between nir-color camera and color camera. in Q Zhang, M Iida & A Mizushima (eds), Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004., 11B, pp. 387-393, International Conference on Automation Technology for Off-road Equipment, ATOE 2004, Kyoto, Japan, 10/7/04.
Chong VK, Kondo N, Ninomiya K, Monta M, Namba K. Comparison on eggplant fruit grading between nir-color camera and color camera. In Zhang Q, Iida M, Mizushima A, editors, Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004. 2004. p. 387-393. 11B
Chong, V. K. ; Kondo, N. ; Ninomiya, K. ; Monta, Mitsuji ; Namba, Kazuhiko. / Comparison on eggplant fruit grading between nir-color camera and color camera. Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004. editor / Q. Zhang ; M. Iida ; A. Mizushima. 2004. pp. 387-393
@inproceedings{3f7b993462cb47f3aaa6af5458bf1d5a,
title = "Comparison on eggplant fruit grading between nir-color camera and color camera",
abstract = "An eggplant grading system was introduced in a JA (agricultural cooperative association) at Okayama, 2002. 6 CCD color cameras were installed to evaluate fruit appearance (fruit color, size, shape, bruise, and diseases), before and after turning over in a line and connected to 2 PCs through 6 image grabber boards, Physical properties of the fruits such as fruit length, average, maximum, and minimum diameters, area, apparent volume, fruit color, calyx color, fruit shape, degree of fruit bend, bruise number, bruise area, and so on were extracted from the images. The 6 CCD color cameras were divided into 2 units, which consisted of 3 cameras each set, were installed for complete surface inspection. However it is not easy to detect several kinds of defects on eggplant fruit surface because the fruit has very dark purple color and several defects are very similar colors with normal skin. In this paper, a new color camera whose sensitivity ranges from visible region to infrared region was used. Most of the fruits have higher spectral reflectance in infrared region (700-1200nm). The color CCD camera had the same G and B components with usual color camera, but R signal includes infrared region was specially ordered. Although a color balance among R, G, and B is lost, it was considered that slight color changes of defects and discrimination from dark background were easier than the usual color CCD camera. HSI and chromaticity conversions were tested as a preprocessing to detect various defects. With the improvement on the detections of bruises and defects, this will further increase the effectiveness of the current eggplant-grading machine.",
keywords = "Eggplant, Grading, Machine vision, Quality evaluation, Spectral reflectance, TV camera",
author = "Chong, {V. K.} and N. Kondo and K. Ninomiya and Mitsuji Monta and Kazuhiko Namba",
year = "2004",
language = "English",
isbn = "189276945X",
pages = "387--393",
editor = "Q. Zhang and M. Iida and A. Mizushima",
booktitle = "Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004",

}

TY - GEN

T1 - Comparison on eggplant fruit grading between nir-color camera and color camera

AU - Chong, V. K.

AU - Kondo, N.

AU - Ninomiya, K.

AU - Monta, Mitsuji

AU - Namba, Kazuhiko

PY - 2004

Y1 - 2004

N2 - An eggplant grading system was introduced in a JA (agricultural cooperative association) at Okayama, 2002. 6 CCD color cameras were installed to evaluate fruit appearance (fruit color, size, shape, bruise, and diseases), before and after turning over in a line and connected to 2 PCs through 6 image grabber boards, Physical properties of the fruits such as fruit length, average, maximum, and minimum diameters, area, apparent volume, fruit color, calyx color, fruit shape, degree of fruit bend, bruise number, bruise area, and so on were extracted from the images. The 6 CCD color cameras were divided into 2 units, which consisted of 3 cameras each set, were installed for complete surface inspection. However it is not easy to detect several kinds of defects on eggplant fruit surface because the fruit has very dark purple color and several defects are very similar colors with normal skin. In this paper, a new color camera whose sensitivity ranges from visible region to infrared region was used. Most of the fruits have higher spectral reflectance in infrared region (700-1200nm). The color CCD camera had the same G and B components with usual color camera, but R signal includes infrared region was specially ordered. Although a color balance among R, G, and B is lost, it was considered that slight color changes of defects and discrimination from dark background were easier than the usual color CCD camera. HSI and chromaticity conversions were tested as a preprocessing to detect various defects. With the improvement on the detections of bruises and defects, this will further increase the effectiveness of the current eggplant-grading machine.

AB - An eggplant grading system was introduced in a JA (agricultural cooperative association) at Okayama, 2002. 6 CCD color cameras were installed to evaluate fruit appearance (fruit color, size, shape, bruise, and diseases), before and after turning over in a line and connected to 2 PCs through 6 image grabber boards, Physical properties of the fruits such as fruit length, average, maximum, and minimum diameters, area, apparent volume, fruit color, calyx color, fruit shape, degree of fruit bend, bruise number, bruise area, and so on were extracted from the images. The 6 CCD color cameras were divided into 2 units, which consisted of 3 cameras each set, were installed for complete surface inspection. However it is not easy to detect several kinds of defects on eggplant fruit surface because the fruit has very dark purple color and several defects are very similar colors with normal skin. In this paper, a new color camera whose sensitivity ranges from visible region to infrared region was used. Most of the fruits have higher spectral reflectance in infrared region (700-1200nm). The color CCD camera had the same G and B components with usual color camera, but R signal includes infrared region was specially ordered. Although a color balance among R, G, and B is lost, it was considered that slight color changes of defects and discrimination from dark background were easier than the usual color CCD camera. HSI and chromaticity conversions were tested as a preprocessing to detect various defects. With the improvement on the detections of bruises and defects, this will further increase the effectiveness of the current eggplant-grading machine.

KW - Eggplant

KW - Grading

KW - Machine vision

KW - Quality evaluation

KW - Spectral reflectance

KW - TV camera

UR - http://www.scopus.com/inward/record.url?scp=27844478856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27844478856&partnerID=8YFLogxK

M3 - Conference contribution

SN - 189276945X

SN - 9781892769459

SP - 387

EP - 393

BT - Proceedings of the International Conference on Automation Technology for Off-road Equipment, ATOE 2004

A2 - Zhang, Q.

A2 - Iida, M.

A2 - Mizushima, A.

ER -