Intelligent classification models for food products basis on morphological, colour and texture features

Narendra Veernagouda Ganganagowder, Priya Kamath

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The aim of this research is to build a supervised intelligent classification model of food products such as Biscuits, Cereals, Vegetables, Edible nuts and etc., using digital images. The Correlation-based Feature Selection (CFS) algorithm and 2nd derivative pre-treatments of the Morphological, Colour and Texture features are used to train the models for classification and detection. The best prediction accuracy is obtained for the Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), Simple Logistic (SLOG) and Sequential Minimal Optimization (SMO) classifiers (more than 80% of the success rate for the training/test set and 80% for the validation set). The percentage of correctly classified instances is very high in these models and ranged from 80% to 96% for the training/test set and up to 95% for the validation set.

Original languageEnglish
JournalActa Agronomica
Volume66
Issue number4
DOIs
Publication statusPublished - 01-01-2017

Fingerprint

foods
texture
color
biscuits
nut
digital images
digital image
nuts
cereal
vegetable
train
logistics
pretreatment
vegetables
testing
prediction
food product
test
support vector machines
support vector machine

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science
  • Soil Science

Cite this

Ganganagowder, Narendra Veernagouda ; Kamath, Priya. / Intelligent classification models for food products basis on morphological, colour and texture features. In: Acta Agronomica. 2017 ; Vol. 66, No. 4.
@article{e4b589ef6ad049b99326ed08081a2864,
title = "Intelligent classification models for food products basis on morphological, colour and texture features",
abstract = "The aim of this research is to build a supervised intelligent classification model of food products such as Biscuits, Cereals, Vegetables, Edible nuts and etc., using digital images. The Correlation-based Feature Selection (CFS) algorithm and 2nd derivative pre-treatments of the Morphological, Colour and Texture features are used to train the models for classification and detection. The best prediction accuracy is obtained for the Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), Simple Logistic (SLOG) and Sequential Minimal Optimization (SMO) classifiers (more than 80{\%} of the success rate for the training/test set and 80{\%} for the validation set). The percentage of correctly classified instances is very high in these models and ranged from 80{\%} to 96{\%} for the training/test set and up to 95{\%} for the validation set.",
author = "Ganganagowder, {Narendra Veernagouda} and Priya Kamath",
year = "2017",
month = "1",
day = "1",
doi = "10.15446/acag.v66n4.60049",
language = "English",
volume = "66",
journal = "Acta Agronomica",
issn = "0044-5959",
publisher = "Universidad Nacional de Colombia",
number = "4",

}

Intelligent classification models for food products basis on morphological, colour and texture features. / Ganganagowder, Narendra Veernagouda; Kamath, Priya.

In: Acta Agronomica, Vol. 66, No. 4, 01.01.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Intelligent classification models for food products basis on morphological, colour and texture features

AU - Ganganagowder, Narendra Veernagouda

AU - Kamath, Priya

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The aim of this research is to build a supervised intelligent classification model of food products such as Biscuits, Cereals, Vegetables, Edible nuts and etc., using digital images. The Correlation-based Feature Selection (CFS) algorithm and 2nd derivative pre-treatments of the Morphological, Colour and Texture features are used to train the models for classification and detection. The best prediction accuracy is obtained for the Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), Simple Logistic (SLOG) and Sequential Minimal Optimization (SMO) classifiers (more than 80% of the success rate for the training/test set and 80% for the validation set). The percentage of correctly classified instances is very high in these models and ranged from 80% to 96% for the training/test set and up to 95% for the validation set.

AB - The aim of this research is to build a supervised intelligent classification model of food products such as Biscuits, Cereals, Vegetables, Edible nuts and etc., using digital images. The Correlation-based Feature Selection (CFS) algorithm and 2nd derivative pre-treatments of the Morphological, Colour and Texture features are used to train the models for classification and detection. The best prediction accuracy is obtained for the Multilayer Perceptron (MLP), Support Vector Machines (SVM), Random Forest (RF), Simple Logistic (SLOG) and Sequential Minimal Optimization (SMO) classifiers (more than 80% of the success rate for the training/test set and 80% for the validation set). The percentage of correctly classified instances is very high in these models and ranged from 80% to 96% for the training/test set and up to 95% for the validation set.

UR - http://www.scopus.com/inward/record.url?scp=85028328702&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028328702&partnerID=8YFLogxK

U2 - 10.15446/acag.v66n4.60049

DO - 10.15446/acag.v66n4.60049

M3 - Article

AN - SCOPUS:85028328702

VL - 66

JO - Acta Agronomica

JF - Acta Agronomica

SN - 0044-5959

IS - 4

ER -