• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.11.2024.tde-12042024-132235
Document
Author
Full name
Luiz Gustavo Schultz Senko
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Piracicaba, 2023
Supervisor
Committee
Gomes Junior, Francisco Guilhien (President)
França Neto, Jose de Barros
Pinheiro, Daniel Teixeira
Title in Portuguese
Desenvolvimento de um sistema automatizado de alto rendimento para avaliação do vigor de sementes de soja
Keywords in Portuguese
Glycine max
Análise de imagens
Germinação
Processamento de imagem
Qualidade de sementes
Vigor de sementes
Abstract in Portuguese
A rapidez e uniformidade de emergência de plântulas em campo são cruciais para um adequado estabelecimento de estande e altas produtividades, estando diretamente relacionadas ao vigor das sementes. Neste cenário, sistemas computadorizados de análise de imagens surgem como alternativas promissoras para melhorar a precisão e velocidade na avaliação do potencial fisiológico de sementes. O objetivo desta pesquisa foi o desenvolvimento do software ProSeedling, especificamente para avaliar o vigor de sementes de soja a partir de imagens de plântulas. A aquisição das imagens das plântulas, com três dias de idade, foi realizada por transiluminação diretamente sobre o papel de germinação. O estudo envolveu dois cultivares de soja, NEO610 IPRO e 0590I2X, totalizando 18 lotes com níveis variados de vigor. Inicialmente, as avaliações foram conduzidas usando o software Vigor-S, estabelecido como referência. Posteriormente, as análises com o ProSeedling forneceram dados para a validação de sua eficiência. Os resultados demonstraram coeficientes de correlação significativos entre as análises do ProSeedling e do Vigor-S, confirmando a acurácia do novo software. Em conclusão, o ProSeedling mostrou-se consistente e confiável na avaliação do vigor de sementes de soja, apresentando-se como um método computadorizado prático, de alto rendimento e baixo custo, com potencial para ser amplamente adotado no campo da pesquisa e produção de sementes.
Title in English
Development of a high-throughput computational system for vigor assessing of soybean seeds
Keywords in English
Glycine max
Germination
Image analysis
Image processing
Seed quality
Seed vigor
Abstract in English
The speed and uniformity of seedling emergence in the field are crucial for proper stand establishment and high yields, directly related to seed vigor. In this scenario, computerized image analysis systems emerge as promising alternatives to enhance accuracy and speed in assessing the physiological potential of seeds. The objective of this research was the development of the ProSeedling software, specifically to evaluate the vigor of soybean seeds from seedling images. The acquisition of the seedling images, at three days old, was done by transillumination directly on the germination paper. The study involved two soybean cultivars, NEO610 IPRO and 0590I2X, totaling 18 lots with varied vigor levels. Initially, evaluations were conducted using the Vigor-S software, established as a reference. Subsequently, analyses with ProSeedling provided data for its efficiency validation. The results showed significant correlation coefficients between the ProSeedling and Vigor-S analyses, confirming the accuracy of the new software. In conclusion, ProSeedling proved to be consistent and reliable in evaluating the vigor of soybean seeds, presenting itself as a practical, high-yield, low-cost computerized method, with potential to be widely adopted in the field of seed research and production.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2024-04-15
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.