Contrast enhancement using brightness preserving histogram equalization technique for classification of date varieties

G. Thomas, A. Manickavasagan, L. Khriji, R. Al-Yahyai

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Computer vision technique is becoming popular for quality assessment of many products in food industries. Image enhancement is the first step in analyzing the images in order to obtain detailed information for the determination of quality. In this study, Brightness preserving histogram equalization technique was used to enhance the features of gray scale images to classify three date varieties (Khalas, Fard and Madina). Mean, entropy, kurtosis and skewness features were extracted from the original and enhanced images. Mean and entropy from original images and kurtosis from the enhanced images were selected based on Lukka's feature selection approach. An overall classification efficiency of 93.72% was achieved with just three features. Brightness preserving histogram equalization technique has great potential to improve the classification in various quality attributes of food and agricultural products with minimum features.

Original languageEnglish
Pages (from-to)55-63
Number of pages9
JournalJournal of Engineering Research
Volume11
Issue number1
Publication statusPublished - 2014

Fingerprint

Luminance
Entropy
Agricultural products
Image enhancement
Computer vision
Feature extraction
Industry

Keywords

  • Brightness preserving histogram equalization
  • Computer vision
  • Dates variety

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Contrast enhancement using brightness preserving histogram equalization technique for classification of date varieties. / Thomas, G.; Manickavasagan, A.; Khriji, L.; Al-Yahyai, R.

In: Journal of Engineering Research, Vol. 11, No. 1, 2014, p. 55-63.

Research output: Contribution to journalArticle

@article{45453b79176749c89d853fe484c60eba,
title = "Contrast enhancement using brightness preserving histogram equalization technique for classification of date varieties",
abstract = "Computer vision technique is becoming popular for quality assessment of many products in food industries. Image enhancement is the first step in analyzing the images in order to obtain detailed information for the determination of quality. In this study, Brightness preserving histogram equalization technique was used to enhance the features of gray scale images to classify three date varieties (Khalas, Fard and Madina). Mean, entropy, kurtosis and skewness features were extracted from the original and enhanced images. Mean and entropy from original images and kurtosis from the enhanced images were selected based on Lukka's feature selection approach. An overall classification efficiency of 93.72{\%} was achieved with just three features. Brightness preserving histogram equalization technique has great potential to improve the classification in various quality attributes of food and agricultural products with minimum features.",
keywords = "Brightness preserving histogram equalization, Computer vision, Dates variety",
author = "G. Thomas and A. Manickavasagan and L. Khriji and R. Al-Yahyai",
year = "2014",
language = "English",
volume = "11",
pages = "55--63",
journal = "Journal of Engineering Research",
issn = "1726-6009",
publisher = "Sultan Qaboos University",
number = "1",

}

TY - JOUR

T1 - Contrast enhancement using brightness preserving histogram equalization technique for classification of date varieties

AU - Thomas, G.

AU - Manickavasagan, A.

AU - Khriji, L.

AU - Al-Yahyai, R.

PY - 2014

Y1 - 2014

N2 - Computer vision technique is becoming popular for quality assessment of many products in food industries. Image enhancement is the first step in analyzing the images in order to obtain detailed information for the determination of quality. In this study, Brightness preserving histogram equalization technique was used to enhance the features of gray scale images to classify three date varieties (Khalas, Fard and Madina). Mean, entropy, kurtosis and skewness features were extracted from the original and enhanced images. Mean and entropy from original images and kurtosis from the enhanced images were selected based on Lukka's feature selection approach. An overall classification efficiency of 93.72% was achieved with just three features. Brightness preserving histogram equalization technique has great potential to improve the classification in various quality attributes of food and agricultural products with minimum features.

AB - Computer vision technique is becoming popular for quality assessment of many products in food industries. Image enhancement is the first step in analyzing the images in order to obtain detailed information for the determination of quality. In this study, Brightness preserving histogram equalization technique was used to enhance the features of gray scale images to classify three date varieties (Khalas, Fard and Madina). Mean, entropy, kurtosis and skewness features were extracted from the original and enhanced images. Mean and entropy from original images and kurtosis from the enhanced images were selected based on Lukka's feature selection approach. An overall classification efficiency of 93.72% was achieved with just three features. Brightness preserving histogram equalization technique has great potential to improve the classification in various quality attributes of food and agricultural products with minimum features.

KW - Brightness preserving histogram equalization

KW - Computer vision

KW - Dates variety

UR - http://www.scopus.com/inward/record.url?scp=84907022717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907022717&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84907022717

VL - 11

SP - 55

EP - 63

JO - Journal of Engineering Research

JF - Journal of Engineering Research

SN - 1726-6009

IS - 1

ER -