Near infrared imaging to detect Aspergillus flavus infection in three varieties of dates

M. Teena, A. Manickavasagan, A. M. Al-Sadi, R. Al-Yahyai, M. L. Deadman, A. Al-Ismaili

Research output: Contribution to journalArticle

Abstract

The present manual sorting technique is not effective to detect fungal infection in dates; especially at the early stage. The potential of near infrared (NIR) area scan imaging (900–1700 nm together as one image) to detect fungal contamination in three popular varieties of dates (Fard, Khalas and Naghal) was investigated. Date samples were treated as three groups: untreated control (UC), sterile control (SC) (surface sterilized, rinsed and dried) and infested samples (IS) (surface sterilized, rinsed, dried and fungal inoculated). The IS was then incubated for 10 days and imaged every 48hr to obtain 5 infection stages namely IS Day2, IS Day4, IS Day6, IS Day8 and IS Day10. In total, 3150 NIR images (UC + SC + five fungal infection stages × 150 images × three date varieties) were acquired and analyzed. The overall highest classification accuracy was 97, 96 and 100% for two-class, six-class and pair-wise models, respectively while comparing IS with UC. Similarly, it was 94, 89 and 94% for two-class, six-class and pair-wise models, respectively while comparing IS with SC. However, when the developed algorithm was tested on pooled dates images (all three varieties combined), the two class model yielded a higher classification accuracy of 83 and 86% for UC and IS, respectively; and 71 and 85% for SC and IS, respectively. Thus, NIR area-scan imaging has the potential to be used as a fast and cheaper technique to detect fungal infection in food industries.

Original languageEnglish
JournalEngineering in Agriculture, Environment and Food
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Aspergillus flavus
Mycoses
Aspergillus
Infrared imaging
dates (fruit)
image analysis
Infection
infection
Food Industry
sampling
Infrared radiation
Control Groups
Imaging techniques
Control surfaces
Sorting
Contamination
sorting
food industry

Keywords

  • Aspergillus flavus
  • Date fruits
  • Fungal infection
  • Near infrared imaging

ASJC Scopus subject areas

  • Food Science
  • Chemical Engineering(all)
  • Industrial and Manufacturing Engineering

Cite this

@article{e05364d6a1f74ebea7c65f099b45bef3,
title = "Near infrared imaging to detect Aspergillus flavus infection in three varieties of dates",
abstract = "The present manual sorting technique is not effective to detect fungal infection in dates; especially at the early stage. The potential of near infrared (NIR) area scan imaging (900–1700 nm together as one image) to detect fungal contamination in three popular varieties of dates (Fard, Khalas and Naghal) was investigated. Date samples were treated as three groups: untreated control (UC), sterile control (SC) (surface sterilized, rinsed and dried) and infested samples (IS) (surface sterilized, rinsed, dried and fungal inoculated). The IS was then incubated for 10 days and imaged every 48hr to obtain 5 infection stages namely IS Day2, IS Day4, IS Day6, IS Day8 and IS Day10. In total, 3150 NIR images (UC + SC + five fungal infection stages × 150 images × three date varieties) were acquired and analyzed. The overall highest classification accuracy was 97, 96 and 100{\%} for two-class, six-class and pair-wise models, respectively while comparing IS with UC. Similarly, it was 94, 89 and 94{\%} for two-class, six-class and pair-wise models, respectively while comparing IS with SC. However, when the developed algorithm was tested on pooled dates images (all three varieties combined), the two class model yielded a higher classification accuracy of 83 and 86{\%} for UC and IS, respectively; and 71 and 85{\%} for SC and IS, respectively. Thus, NIR area-scan imaging has the potential to be used as a fast and cheaper technique to detect fungal infection in food industries.",
keywords = "Aspergillus flavus, Date fruits, Fungal infection, Near infrared imaging",
author = "M. Teena and A. Manickavasagan and Al-Sadi, {A. M.} and R. Al-Yahyai and Deadman, {M. L.} and A. Al-Ismaili",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.eaef.2018.04.002",
language = "English",
journal = "Engineering in Agriculture, Environment and Food",
issn = "1881-8366",
publisher = "Asian Agricultural and Biological Engineering Association",

}

TY - JOUR

T1 - Near infrared imaging to detect Aspergillus flavus infection in three varieties of dates

AU - Teena, M.

AU - Manickavasagan, A.

AU - Al-Sadi, A. M.

AU - Al-Yahyai, R.

AU - Deadman, M. L.

AU - Al-Ismaili, A.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The present manual sorting technique is not effective to detect fungal infection in dates; especially at the early stage. The potential of near infrared (NIR) area scan imaging (900–1700 nm together as one image) to detect fungal contamination in three popular varieties of dates (Fard, Khalas and Naghal) was investigated. Date samples were treated as three groups: untreated control (UC), sterile control (SC) (surface sterilized, rinsed and dried) and infested samples (IS) (surface sterilized, rinsed, dried and fungal inoculated). The IS was then incubated for 10 days and imaged every 48hr to obtain 5 infection stages namely IS Day2, IS Day4, IS Day6, IS Day8 and IS Day10. In total, 3150 NIR images (UC + SC + five fungal infection stages × 150 images × three date varieties) were acquired and analyzed. The overall highest classification accuracy was 97, 96 and 100% for two-class, six-class and pair-wise models, respectively while comparing IS with UC. Similarly, it was 94, 89 and 94% for two-class, six-class and pair-wise models, respectively while comparing IS with SC. However, when the developed algorithm was tested on pooled dates images (all three varieties combined), the two class model yielded a higher classification accuracy of 83 and 86% for UC and IS, respectively; and 71 and 85% for SC and IS, respectively. Thus, NIR area-scan imaging has the potential to be used as a fast and cheaper technique to detect fungal infection in food industries.

AB - The present manual sorting technique is not effective to detect fungal infection in dates; especially at the early stage. The potential of near infrared (NIR) area scan imaging (900–1700 nm together as one image) to detect fungal contamination in three popular varieties of dates (Fard, Khalas and Naghal) was investigated. Date samples were treated as three groups: untreated control (UC), sterile control (SC) (surface sterilized, rinsed and dried) and infested samples (IS) (surface sterilized, rinsed, dried and fungal inoculated). The IS was then incubated for 10 days and imaged every 48hr to obtain 5 infection stages namely IS Day2, IS Day4, IS Day6, IS Day8 and IS Day10. In total, 3150 NIR images (UC + SC + five fungal infection stages × 150 images × three date varieties) were acquired and analyzed. The overall highest classification accuracy was 97, 96 and 100% for two-class, six-class and pair-wise models, respectively while comparing IS with UC. Similarly, it was 94, 89 and 94% for two-class, six-class and pair-wise models, respectively while comparing IS with SC. However, when the developed algorithm was tested on pooled dates images (all three varieties combined), the two class model yielded a higher classification accuracy of 83 and 86% for UC and IS, respectively; and 71 and 85% for SC and IS, respectively. Thus, NIR area-scan imaging has the potential to be used as a fast and cheaper technique to detect fungal infection in food industries.

KW - Aspergillus flavus

KW - Date fruits

KW - Fungal infection

KW - Near infrared imaging

UR - http://www.scopus.com/inward/record.url?scp=85046124480&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046124480&partnerID=8YFLogxK

U2 - 10.1016/j.eaef.2018.04.002

DO - 10.1016/j.eaef.2018.04.002

M3 - Article

AN - SCOPUS:85046124480

JO - Engineering in Agriculture, Environment and Food

JF - Engineering in Agriculture, Environment and Food

SN - 1881-8366

ER -