Geometry-based mass grading of mango fruits using image processing

M. A. Momin, M. T. Rahman, M. S. Sultana, C. Igathinathane, A. T.M. Ziauddin, T. E. Grift

Research output: Contribution to journalArticle

Abstract

Mango (Mangifera indica) is an important, and popular fruit in Bangladesh. However, the post-harvest processing of it is still mostly performed manually, a situation far from satisfactory, in terms of accuracy and throughput. To automate the grading of mangos (geometry and shape), we developed an image acquisition and processing system to extract projected area, perimeter, and roundness features. In this system, images were acquired using a XGA format color camera of 8-bit gray levels using fluorescent lighting. An image processing algorithm based on region based global thresholding color binarization, combined with median filter and morphological analysis was developed to classify mangos into one of three mass grades such as large, medium, and small. This system achieved an accuracy of 97% for projected area and Feret diameter, 79% for perimeter, and 36% for roundness. To achieve a finer grading, two different grading features could be used in sequence. The image grading system is simple and efficient and can be considered a suitable first stage to mechanizing the commercial grading of mangos in Bangladesh. Moreover, the method has the potential to be applied to other crops with suitable adjustments.

Original languageEnglish (US)
Pages (from-to)150-160
Number of pages11
JournalInformation Processing in Agriculture
Volume4
Issue number2
DOIs
StatePublished - Jun 2017

Fingerprint

Fruits
mangoes
image processing
Image processing
fruit
image analysis
geometry
fruits
Geometry
Bangladesh
fluorescent lighting
color
Mangifera indica
Color
Median filters
cameras
Image acquisition
filter
crop
Crops

Keywords

  • Horticultural crops
  • Quality
  • Sorting

ASJC Scopus subject areas

  • Forestry
  • Aquatic Science
  • Animal Science and Zoology
  • Agronomy and Crop Science
  • Computer Science Applications

Cite this

Momin, M. A., Rahman, M. T., Sultana, M. S., Igathinathane, C., Ziauddin, A. T. M., & Grift, T. E. (2017). Geometry-based mass grading of mango fruits using image processing. Information Processing in Agriculture, 4(2), 150-160. https://doi.org/10.1016/j.inpa.2017.03.003

Geometry-based mass grading of mango fruits using image processing. / Momin, M. A.; Rahman, M. T.; Sultana, M. S.; Igathinathane, C.; Ziauddin, A. T.M.; Grift, T. E.

In: Information Processing in Agriculture, Vol. 4, No. 2, 06.2017, p. 150-160.

Research output: Contribution to journalArticle

Momin, MA, Rahman, MT, Sultana, MS, Igathinathane, C, Ziauddin, ATM & Grift, TE 2017, 'Geometry-based mass grading of mango fruits using image processing', Information Processing in Agriculture, vol. 4, no. 2, pp. 150-160. https://doi.org/10.1016/j.inpa.2017.03.003
Momin, M. A. ; Rahman, M. T. ; Sultana, M. S. ; Igathinathane, C. ; Ziauddin, A. T.M. ; Grift, T. E. / Geometry-based mass grading of mango fruits using image processing. In: Information Processing in Agriculture. 2017 ; Vol. 4, No. 2. pp. 150-160.
@article{7655dcc7429640bcb1cf5a3947fcabf9,
title = "Geometry-based mass grading of mango fruits using image processing",
abstract = "Mango (Mangifera indica) is an important, and popular fruit in Bangladesh. However, the post-harvest processing of it is still mostly performed manually, a situation far from satisfactory, in terms of accuracy and throughput. To automate the grading of mangos (geometry and shape), we developed an image acquisition and processing system to extract projected area, perimeter, and roundness features. In this system, images were acquired using a XGA format color camera of 8-bit gray levels using fluorescent lighting. An image processing algorithm based on region based global thresholding color binarization, combined with median filter and morphological analysis was developed to classify mangos into one of three mass grades such as large, medium, and small. This system achieved an accuracy of 97{\%} for projected area and Feret diameter, 79{\%} for perimeter, and 36{\%} for roundness. To achieve a finer grading, two different grading features could be used in sequence. The image grading system is simple and efficient and can be considered a suitable first stage to mechanizing the commercial grading of mangos in Bangladesh. Moreover, the method has the potential to be applied to other crops with suitable adjustments.",
keywords = "Horticultural crops, Quality, Sorting",
author = "Momin, {M. A.} and Rahman, {M. T.} and Sultana, {M. S.} and C. Igathinathane and Ziauddin, {A. T.M.} and Grift, {T. E.}",
year = "2017",
month = "6",
doi = "10.1016/j.inpa.2017.03.003",
language = "English (US)",
volume = "4",
pages = "150--160",
journal = "Information Processing in Agriculture",
issn = "2214-3173",
publisher = "Elsevier BV",
number = "2",

}

TY - JOUR

T1 - Geometry-based mass grading of mango fruits using image processing

AU - Momin, M. A.

AU - Rahman, M. T.

AU - Sultana, M. S.

AU - Igathinathane, C.

AU - Ziauddin, A. T.M.

AU - Grift, T. E.

PY - 2017/6

Y1 - 2017/6

N2 - Mango (Mangifera indica) is an important, and popular fruit in Bangladesh. However, the post-harvest processing of it is still mostly performed manually, a situation far from satisfactory, in terms of accuracy and throughput. To automate the grading of mangos (geometry and shape), we developed an image acquisition and processing system to extract projected area, perimeter, and roundness features. In this system, images were acquired using a XGA format color camera of 8-bit gray levels using fluorescent lighting. An image processing algorithm based on region based global thresholding color binarization, combined with median filter and morphological analysis was developed to classify mangos into one of three mass grades such as large, medium, and small. This system achieved an accuracy of 97% for projected area and Feret diameter, 79% for perimeter, and 36% for roundness. To achieve a finer grading, two different grading features could be used in sequence. The image grading system is simple and efficient and can be considered a suitable first stage to mechanizing the commercial grading of mangos in Bangladesh. Moreover, the method has the potential to be applied to other crops with suitable adjustments.

AB - Mango (Mangifera indica) is an important, and popular fruit in Bangladesh. However, the post-harvest processing of it is still mostly performed manually, a situation far from satisfactory, in terms of accuracy and throughput. To automate the grading of mangos (geometry and shape), we developed an image acquisition and processing system to extract projected area, perimeter, and roundness features. In this system, images were acquired using a XGA format color camera of 8-bit gray levels using fluorescent lighting. An image processing algorithm based on region based global thresholding color binarization, combined with median filter and morphological analysis was developed to classify mangos into one of three mass grades such as large, medium, and small. This system achieved an accuracy of 97% for projected area and Feret diameter, 79% for perimeter, and 36% for roundness. To achieve a finer grading, two different grading features could be used in sequence. The image grading system is simple and efficient and can be considered a suitable first stage to mechanizing the commercial grading of mangos in Bangladesh. Moreover, the method has the potential to be applied to other crops with suitable adjustments.

KW - Horticultural crops

KW - Quality

KW - Sorting

UR - http://www.scopus.com/inward/record.url?scp=85017556502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017556502&partnerID=8YFLogxK

U2 - 10.1016/j.inpa.2017.03.003

DO - 10.1016/j.inpa.2017.03.003

M3 - Article

AN - SCOPUS:85017556502

VL - 4

SP - 150

EP - 160

JO - Information Processing in Agriculture

JF - Information Processing in Agriculture

SN - 2214-3173

IS - 2

ER -