Detectar e classificar castanhas de caju, tipo inteiro branco, através de rede neural artificial

Translated title of the contribution: Recognition and classification of White Wholes (WW) grade cashew kernel using artificial neural networks

Narendra Veranagouda Ganganagowdar, Hareesha Katiganere Siddaramappa

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A novel intelligent automated model to recognize and classify a cashew kernels using Artificial Neural Network (ANN). The model primarily intends to work on two phases. The phase one, built with a proposed method to extract features, which includes 16 morphological features and also 24 color features from the input cashew kernel images. In phase two, a Multilayer Perceptron ANN is being used to recognize and classify the given white wholes grades using back propagation learning algorithm. The proposed method achieves a classification accuracy of 88.93%. This study also reveals that the combination of morphological and color features outperforms rather using any one set of features separately to grade cashew kernels.

Original languagePortuguese
Pages (from-to)145-155
Number of pages11
JournalActa Scientiarum - Agronomy
Volume38
Issue number2
DOIs
Publication statusPublished - 01-04-2016

Fingerprint

neural networks
seeds
color
learning
extracts
methodology

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science

Cite this

Ganganagowdar, Narendra Veranagouda ; Siddaramappa, Hareesha Katiganere. / Detectar e classificar castanhas de caju, tipo inteiro branco, através de rede neural artificial. In: Acta Scientiarum - Agronomy. 2016 ; Vol. 38, No. 2. pp. 145-155.
@article{46057c254eeb41859b969d7b96b82172,
title = "Detectar e classificar castanhas de caju, tipo inteiro branco, atrav{\'e}s de rede neural artificial",
abstract = "A novel intelligent automated model to recognize and classify a cashew kernels using Artificial Neural Network (ANN). The model primarily intends to work on two phases. The phase one, built with a proposed method to extract features, which includes 16 morphological features and also 24 color features from the input cashew kernel images. In phase two, a Multilayer Perceptron ANN is being used to recognize and classify the given white wholes grades using back propagation learning algorithm. The proposed method achieves a classification accuracy of 88.93{\%}. This study also reveals that the combination of morphological and color features outperforms rather using any one set of features separately to grade cashew kernels.",
author = "Ganganagowdar, {Narendra Veranagouda} and Siddaramappa, {Hareesha Katiganere}",
year = "2016",
month = "4",
day = "1",
doi = "10.4025/actasciagron.v38i2.27861",
language = "Portuguese",
volume = "38",
pages = "145--155",
journal = "Acta Scientiarum - Agronomy",
issn = "1679-9275",
publisher = "Universidade Estadual de Maringa",
number = "2",

}

Detectar e classificar castanhas de caju, tipo inteiro branco, através de rede neural artificial. / Ganganagowdar, Narendra Veranagouda; Siddaramappa, Hareesha Katiganere.

In: Acta Scientiarum - Agronomy, Vol. 38, No. 2, 01.04.2016, p. 145-155.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detectar e classificar castanhas de caju, tipo inteiro branco, através de rede neural artificial

AU - Ganganagowdar, Narendra Veranagouda

AU - Siddaramappa, Hareesha Katiganere

PY - 2016/4/1

Y1 - 2016/4/1

N2 - A novel intelligent automated model to recognize and classify a cashew kernels using Artificial Neural Network (ANN). The model primarily intends to work on two phases. The phase one, built with a proposed method to extract features, which includes 16 morphological features and also 24 color features from the input cashew kernel images. In phase two, a Multilayer Perceptron ANN is being used to recognize and classify the given white wholes grades using back propagation learning algorithm. The proposed method achieves a classification accuracy of 88.93%. This study also reveals that the combination of morphological and color features outperforms rather using any one set of features separately to grade cashew kernels.

AB - A novel intelligent automated model to recognize and classify a cashew kernels using Artificial Neural Network (ANN). The model primarily intends to work on two phases. The phase one, built with a proposed method to extract features, which includes 16 morphological features and also 24 color features from the input cashew kernel images. In phase two, a Multilayer Perceptron ANN is being used to recognize and classify the given white wholes grades using back propagation learning algorithm. The proposed method achieves a classification accuracy of 88.93%. This study also reveals that the combination of morphological and color features outperforms rather using any one set of features separately to grade cashew kernels.

UR - http://www.scopus.com/inward/record.url?scp=84963854390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963854390&partnerID=8YFLogxK

U2 - 10.4025/actasciagron.v38i2.27861

DO - 10.4025/actasciagron.v38i2.27861

M3 - Article

AN - SCOPUS:84963854390

VL - 38

SP - 145

EP - 155

JO - Acta Scientiarum - Agronomy

JF - Acta Scientiarum - Agronomy

SN - 1679-9275

IS - 2

ER -