Edge Detection Features to Evaluate Hardness of Dates Using Monochrome Images

A. Manickavasagan, H. N. Al-Shekaili, G. Thomas, M. S. Rahman, N. Guizani, D. S. Jayas

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Date is an important fruit in the regular diets of many peoples in the Arab countries and several other parts of the world. Hardness is one of the important attributes in determining the quality of dates. Hard dates are tough, difficult to chew, unsuitable for several product preparation and ultimately fetching low market price. In general, hard dates have strong curvy and zigzag textured skin. In this study, the efficiency of edge detection features in classifying dates based on hardness using monochrome images was determined. Date samples (Fard variety) were obtained from three major dates growing regions in Oman, and classified into three grades (soft, semi-hard and hard) by a group of trained graders followed with a confirmation by an experienced grader in a commercial dates company. Individual dates were imaged using a monochrome camera (600 dates per grade; total = 1,800 images). A total of 36 features were extracted (28 in spatial domain and 8 in frequency domain) using edge detection methods. An artificial neural network (ANN) was used to classify the dates based on hardness. The overall classification accuracies were 75 % and 87 % while using single ANN (irrespective of regions) for three-class (soft, semi-hard and hard) and two-class (soft and hard (semi-hard and hard together)) models, respectively. While using separate ANN for each region in the three-class model, the mean classification accuracies were 94 %, 59 % and 84 % for soft, semi-hard and hard dates, respectively. Similarly, for the two-class ANN model for each region, the accuracies were 95 % and 77 % for soft and hard dates, respectively. Edge detection features have a great potential in determining several surface qualities of food and agricultural products, where similar gray or color values but varying texture are found.

Original languageEnglish
Pages (from-to)2251-2258
Number of pages8
JournalFood and Bioprocess Technology
Volume7
Issue number8
DOIs
Publication statusPublished - 2014

Fingerprint

Hardness
dates (fruit)
Edge detection
neural networks
hardness
Neural networks
Oman
Food Quality
Arab countries
Neural Networks (Computer)
Middle East
surface quality
Agricultural products
market prices
Fruit
Nutrition
agricultural products
Color
Fruits
cameras

Keywords

  • Canny
  • Dates
  • Hardness
  • Roberts
  • Sobel

ASJC Scopus subject areas

  • Food Science
  • Process Chemistry and Technology
  • Safety, Risk, Reliability and Quality
  • Industrial and Manufacturing Engineering

Cite this

Edge Detection Features to Evaluate Hardness of Dates Using Monochrome Images. / Manickavasagan, A.; Al-Shekaili, H. N.; Thomas, G.; Rahman, M. S.; Guizani, N.; Jayas, D. S.

In: Food and Bioprocess Technology, Vol. 7, No. 8, 2014, p. 2251-2258.

Research output: Contribution to journalArticle

Manickavasagan, A. ; Al-Shekaili, H. N. ; Thomas, G. ; Rahman, M. S. ; Guizani, N. ; Jayas, D. S. / Edge Detection Features to Evaluate Hardness of Dates Using Monochrome Images. In: Food and Bioprocess Technology. 2014 ; Vol. 7, No. 8. pp. 2251-2258.
@article{1f7165772a9b4aa8a3fd181290045f6f,
title = "Edge Detection Features to Evaluate Hardness of Dates Using Monochrome Images",
abstract = "Date is an important fruit in the regular diets of many peoples in the Arab countries and several other parts of the world. Hardness is one of the important attributes in determining the quality of dates. Hard dates are tough, difficult to chew, unsuitable for several product preparation and ultimately fetching low market price. In general, hard dates have strong curvy and zigzag textured skin. In this study, the efficiency of edge detection features in classifying dates based on hardness using monochrome images was determined. Date samples (Fard variety) were obtained from three major dates growing regions in Oman, and classified into three grades (soft, semi-hard and hard) by a group of trained graders followed with a confirmation by an experienced grader in a commercial dates company. Individual dates were imaged using a monochrome camera (600 dates per grade; total = 1,800 images). A total of 36 features were extracted (28 in spatial domain and 8 in frequency domain) using edge detection methods. An artificial neural network (ANN) was used to classify the dates based on hardness. The overall classification accuracies were 75 {\%} and 87 {\%} while using single ANN (irrespective of regions) for three-class (soft, semi-hard and hard) and two-class (soft and hard (semi-hard and hard together)) models, respectively. While using separate ANN for each region in the three-class model, the mean classification accuracies were 94 {\%}, 59 {\%} and 84 {\%} for soft, semi-hard and hard dates, respectively. Similarly, for the two-class ANN model for each region, the accuracies were 95 {\%} and 77 {\%} for soft and hard dates, respectively. Edge detection features have a great potential in determining several surface qualities of food and agricultural products, where similar gray or color values but varying texture are found.",
keywords = "Canny, Dates, Hardness, Roberts, Sobel",
author = "A. Manickavasagan and Al-Shekaili, {H. N.} and G. Thomas and Rahman, {M. S.} and N. Guizani and Jayas, {D. S.}",
year = "2014",
doi = "10.1007/s11947-013-1219-0",
language = "English",
volume = "7",
pages = "2251--2258",
journal = "Food and Bioprocess Technology",
issn = "1935-5130",
publisher = "Springer New York",
number = "8",

}

TY - JOUR

T1 - Edge Detection Features to Evaluate Hardness of Dates Using Monochrome Images

AU - Manickavasagan, A.

AU - Al-Shekaili, H. N.

AU - Thomas, G.

AU - Rahman, M. S.

AU - Guizani, N.

AU - Jayas, D. S.

PY - 2014

Y1 - 2014

N2 - Date is an important fruit in the regular diets of many peoples in the Arab countries and several other parts of the world. Hardness is one of the important attributes in determining the quality of dates. Hard dates are tough, difficult to chew, unsuitable for several product preparation and ultimately fetching low market price. In general, hard dates have strong curvy and zigzag textured skin. In this study, the efficiency of edge detection features in classifying dates based on hardness using monochrome images was determined. Date samples (Fard variety) were obtained from three major dates growing regions in Oman, and classified into three grades (soft, semi-hard and hard) by a group of trained graders followed with a confirmation by an experienced grader in a commercial dates company. Individual dates were imaged using a monochrome camera (600 dates per grade; total = 1,800 images). A total of 36 features were extracted (28 in spatial domain and 8 in frequency domain) using edge detection methods. An artificial neural network (ANN) was used to classify the dates based on hardness. The overall classification accuracies were 75 % and 87 % while using single ANN (irrespective of regions) for three-class (soft, semi-hard and hard) and two-class (soft and hard (semi-hard and hard together)) models, respectively. While using separate ANN for each region in the three-class model, the mean classification accuracies were 94 %, 59 % and 84 % for soft, semi-hard and hard dates, respectively. Similarly, for the two-class ANN model for each region, the accuracies were 95 % and 77 % for soft and hard dates, respectively. Edge detection features have a great potential in determining several surface qualities of food and agricultural products, where similar gray or color values but varying texture are found.

AB - Date is an important fruit in the regular diets of many peoples in the Arab countries and several other parts of the world. Hardness is one of the important attributes in determining the quality of dates. Hard dates are tough, difficult to chew, unsuitable for several product preparation and ultimately fetching low market price. In general, hard dates have strong curvy and zigzag textured skin. In this study, the efficiency of edge detection features in classifying dates based on hardness using monochrome images was determined. Date samples (Fard variety) were obtained from three major dates growing regions in Oman, and classified into three grades (soft, semi-hard and hard) by a group of trained graders followed with a confirmation by an experienced grader in a commercial dates company. Individual dates were imaged using a monochrome camera (600 dates per grade; total = 1,800 images). A total of 36 features were extracted (28 in spatial domain and 8 in frequency domain) using edge detection methods. An artificial neural network (ANN) was used to classify the dates based on hardness. The overall classification accuracies were 75 % and 87 % while using single ANN (irrespective of regions) for three-class (soft, semi-hard and hard) and two-class (soft and hard (semi-hard and hard together)) models, respectively. While using separate ANN for each region in the three-class model, the mean classification accuracies were 94 %, 59 % and 84 % for soft, semi-hard and hard dates, respectively. Similarly, for the two-class ANN model for each region, the accuracies were 95 % and 77 % for soft and hard dates, respectively. Edge detection features have a great potential in determining several surface qualities of food and agricultural products, where similar gray or color values but varying texture are found.

KW - Canny

KW - Dates

KW - Hardness

KW - Roberts

KW - Sobel

UR - http://www.scopus.com/inward/record.url?scp=84903716244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903716244&partnerID=8YFLogxK

U2 - 10.1007/s11947-013-1219-0

DO - 10.1007/s11947-013-1219-0

M3 - Article

VL - 7

SP - 2251

EP - 2258

JO - Food and Bioprocess Technology

JF - Food and Bioprocess Technology

SN - 1935-5130

IS - 8

ER -