Advanced phenotyping in tomato fruit classification through artificial intelligence

ABSTRACT: The tomato (Solanum lycopersicum L.) plays a vital role in global agriculture and is a model organism in genetic studies. Visual classification of tomatoes for genetic improvement programs faces challenges due to variety diversity, uneven ripening, external damages, and evaluator subjectiv...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandra Eulália Santos Faria, Alcinei Místico Azevedo, Nayany Gomes Rabelo, Varlen Zeferino Anastácio, Valentina de Melo Maciel, Deltimara Viana Matos, Elias Barbosa Rodrigues, Phelipe Souza Amorim, Janete Ramos da Silva, Fernanda de Souza Santos
Format: Article
Language:English
Published: Universidade de São Paulo 2024-11-01
Series:Scientia Agricola
Subjects:
Online Access:http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162025000101101&lng=en&tlng=en
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846119106511634432
author Sandra Eulália Santos Faria
Alcinei Místico Azevedo
Nayany Gomes Rabelo
Varlen Zeferino Anastácio
Valentina de Melo Maciel
Deltimara Viana Matos
Elias Barbosa Rodrigues
Phelipe Souza Amorim
Janete Ramos da Silva
Fernanda de Souza Santos
author_facet Sandra Eulália Santos Faria
Alcinei Místico Azevedo
Nayany Gomes Rabelo
Varlen Zeferino Anastácio
Valentina de Melo Maciel
Deltimara Viana Matos
Elias Barbosa Rodrigues
Phelipe Souza Amorim
Janete Ramos da Silva
Fernanda de Souza Santos
author_sort Sandra Eulália Santos Faria
collection DOAJ
description ABSTRACT: The tomato (Solanum lycopersicum L.) plays a vital role in global agriculture and is a model organism in genetic studies. Visual classification of tomatoes for genetic improvement programs faces challenges due to variety diversity, uneven ripening, external damages, and evaluator subjectivity. Recent advances in the field of computational resources, such as image phenotyping have enabled pre- and post-harvest assessments that are both fast and precise. This study aimed to classify tomato fruits based on shape, group, color, and defects using Convolutional Neural Networks (CNNs). The performance of five architectures - VGG16, InceptionV3, ResNet50, EfficientNetB3, and InceptionResNetV2 was evaluated to identify and determine the most efficient one for this classification. The research considered ten hybrids and their five parental lines. The experiment was conducted in the field, and images of ripe fruits were acquired using a portable mini studio. The ExpImage package in R software was used for fruit individualization by image and to aid in creating a synthetic database for network training. Images were grouped according to their classifications in terms of shape, color, groups, and defects. The InceptionResNetV2 architecture was the most efficient, achieving metrics such as precision and recall exceeding 93 % for most analyzed variables, and shorter classification times. This study advances the understanding of CNN applications in agriculture and research and provides valuable guidelines for optimizing classification tasks in distinct types of fruits.
format Article
id doaj-art-54c26820c02f4e7b84fa5f83d75c8cf1
institution Kabale University
issn 1678-992X
language English
publishDate 2024-11-01
publisher Universidade de São Paulo
record_format Article
series Scientia Agricola
spelling doaj-art-54c26820c02f4e7b84fa5f83d75c8cf12024-12-17T07:47:47ZengUniversidade de São PauloScientia Agricola1678-992X2024-11-018210.1590/1678-992x-2024-0115Advanced phenotyping in tomato fruit classification through artificial intelligenceSandra Eulália Santos Fariahttps://orcid.org/0000-0001-8773-7539Alcinei Místico Azevedohttps://orcid.org/0000-0001-5196-0851Nayany Gomes Rabelohttps://orcid.org/0009-0001-9018-6640Varlen Zeferino Anastáciohttps://orcid.org/0009-0000-0078-6806Valentina de Melo Macielhttps://orcid.org/0009-0009-1787-1404Deltimara Viana Matoshttps://orcid.org/0009-0001-1989-8389Elias Barbosa Rodrigueshttps://orcid.org/0000-0003-4837-8961Phelipe Souza Amorimhttps://orcid.org/0009-0003-5247-6975Janete Ramos da Silvahttps://orcid.org/0000-0001-6168-3368Fernanda de Souza Santoshttps://orcid.org/0009-0002-8297-3430ABSTRACT: The tomato (Solanum lycopersicum L.) plays a vital role in global agriculture and is a model organism in genetic studies. Visual classification of tomatoes for genetic improvement programs faces challenges due to variety diversity, uneven ripening, external damages, and evaluator subjectivity. Recent advances in the field of computational resources, such as image phenotyping have enabled pre- and post-harvest assessments that are both fast and precise. This study aimed to classify tomato fruits based on shape, group, color, and defects using Convolutional Neural Networks (CNNs). The performance of five architectures - VGG16, InceptionV3, ResNet50, EfficientNetB3, and InceptionResNetV2 was evaluated to identify and determine the most efficient one for this classification. The research considered ten hybrids and their five parental lines. The experiment was conducted in the field, and images of ripe fruits were acquired using a portable mini studio. The ExpImage package in R software was used for fruit individualization by image and to aid in creating a synthetic database for network training. Images were grouped according to their classifications in terms of shape, color, groups, and defects. The InceptionResNetV2 architecture was the most efficient, achieving metrics such as precision and recall exceeding 93 % for most analyzed variables, and shorter classification times. This study advances the understanding of CNN applications in agriculture and research and provides valuable guidelines for optimizing classification tasks in distinct types of fruits.http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162025000101101&lng=en&tlng=enSolanum lycopersicum Limage analysisdeep learningtomato breedingneural networks
spellingShingle Sandra Eulália Santos Faria
Alcinei Místico Azevedo
Nayany Gomes Rabelo
Varlen Zeferino Anastácio
Valentina de Melo Maciel
Deltimara Viana Matos
Elias Barbosa Rodrigues
Phelipe Souza Amorim
Janete Ramos da Silva
Fernanda de Souza Santos
Advanced phenotyping in tomato fruit classification through artificial intelligence
Scientia Agricola
Solanum lycopersicum L
image analysis
deep learning
tomato breeding
neural networks
title Advanced phenotyping in tomato fruit classification through artificial intelligence
title_full Advanced phenotyping in tomato fruit classification through artificial intelligence
title_fullStr Advanced phenotyping in tomato fruit classification through artificial intelligence
title_full_unstemmed Advanced phenotyping in tomato fruit classification through artificial intelligence
title_short Advanced phenotyping in tomato fruit classification through artificial intelligence
title_sort advanced phenotyping in tomato fruit classification through artificial intelligence
topic Solanum lycopersicum L
image analysis
deep learning
tomato breeding
neural networks
url http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162025000101101&lng=en&tlng=en
work_keys_str_mv AT sandraeulaliasantosfaria advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT alcineimisticoazevedo advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT nayanygomesrabelo advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT varlenzeferinoanastacio advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT valentinademelomaciel advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT deltimaravianamatos advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT eliasbarbosarodrigues advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT phelipesouzaamorim advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT janeteramosdasilva advancedphenotypingintomatofruitclassificationthroughartificialintelligence
AT fernandadesouzasantos advancedphenotypingintomatofruitclassificationthroughartificialintelligence