Detalhes bibliográficos
Ano de defesa: |
2018 |
Autor(a) principal: |
Lins, Elison Alfeu
 |
Orientador(a): |
Rieder, Rafael
 |
Banca de defesa: |
Não Informado pela instituição |
Tipo de documento: |
Dissertação
|
Tipo de acesso: |
Acesso aberto |
Idioma: |
por |
Instituição de defesa: |
Universidade de Passo Fundo
|
Programa de Pós-Graduação: |
Programa de Pós-Graduação em Computação Aplicada
|
Departamento: |
Instituto de Ciências Exatas e Geociências – ICEG
|
País: |
Brasil
|
Palavras-chave em Português: |
|
Área do conhecimento CNPq: |
|
Link de acesso: |
http://tede.upf.br/jspui/handle/tede/1505
|
Resumo: |
Aphids are insects that attack crops and cause damage directly, consuming the sap of plants, and indirectly, transmitting diseases. The counting and classification of these insects are fundamental for measuring and predicting crop hazards and serving as the basis for the application or not of chemicals, also, to test plant resistance. Traditionally, the counting process is manual, and depends of microscopes and good eyesight of the specialist, in a time consuming task susceptible to errors. With this in mind, this paper presents a methodology and a software to automate the counting and classification of aphids of specie Rhopalosiphum padi using image processing, computer vision and deep learning methods. The text also presents a system analysis, using 40 samples, comparing manually counts and values obtained with software. As a result, we obtain a strong positive correlation in count and classification stage (R = 0,92579) and measurement stage (R = 0,9799). |