coffee-phytopathology-detection

This is my graduation project. The objective is to detect the disease in the coffee leaf and the contamination percentage.

https://github.com/lucs1590/coffee-phytopathology-detection

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

This is my graduation project. The objective is to detect the disease in the coffee leaf and the contamination percentage.

Basic Info
  • Host: GitHub
  • Owner: Lucs1590
  • Default Branch: master
  • Size: 991 KB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 6 years ago · Last pushed about 2 years ago
Metadata Files
Readme Citation

README.md

Inteligência artificial para a identificação e quantificação de ferrugem e bicho mineiro na cultura do café

ÁLVARO LEANDRO CAVALCANTE CARNEIRO¹; LUCAS DE SILVA BRITO²; MARISA SILVEIRA ALMEIDA RENAUD FAULIN³; JOÃO RICARDO FAVAN³.

¹ Discente em Big Data no Agronegócio na FATEC Pompéia “Shunji Nishimura”, Pompéia-SP, Fone: (14) 996254788, leandro0807@live.com'

² Discente em Big Data no Agronegócio na FATEC Pompéia “Shunji Nishimura”, Pompéia-SP, Fone: (14) 997270606, lucasbsilva29@gmail.com'

³ Docentes do curso Big Data no Agronegócio, FATEC Pompéia, Pompéia-SP.

RESUMO: O controle de pragas e doenças desempenham um papel fundamental na agricultura, anualmente milhões de reais são gastos devido aos danos causados por esses agentes. Porém, diversos avanços estão sendo feitos nas áreas de visão computacional e deep learning, devido a criação de novos algoritmos e ao aumento do poder de processamento dos computadores modernos. Partindo desse pressuposto, o objetivo da pesquisa foi I) criar um algoritmo capaz de identificar e localizar diferentes problemas fitossanitários nas folhas do café (Coffea arabica) e II) quantificar a severidade de ferrugem do cafeeiro presente na folha. Para isso foram utilizados diferentes arquiteturas de redes neurais convolucionais, linguagem de programação Python, a biblioteca OpenCV e o algoritmo k-means (K-médias). Os resultados mostram uma precisão média de 81% no acerto da classificação e localização das fitossanidades nas folhas, considerando um threshold de união sobre intersecção de 50%. Em relação à quantificação da severidade, foi obtido um acerto médio de 38,9% com baixa diferença significativa em relação aos sistemas de cores e software testados, segundo comparação com teste de Tukey a 5% de probabilidade, levando em conta a acuidade visual, a partir de uma escala diagramática.

Palavras-chave: deep learning. detecção de objetos. visão computacional. entomologia. fitopatologia.


ABSTRACT: Pest and disease control play a key role in agriculture, millions of dollars are spent annually due to the damage caused by these agents. However, several advances are being made in the areas of computer vision and deep learning, due to the creation of new algorithms and the increased processing power of modern computers. Based on this assumption, the aim of this research was to I) create an algorithm capable of identifying and locating different phytosanitary problems in coffee leaves (Coffea arabica) and II) quantifying the severity of coffee leaf rust. Different convolutional neural network architectures, Python programming language, OpenCV library and k-means algorithm were used. The results show an average accuracy of 81% in the classification and localization of the leaves phytosanitary, considering 50% of union over intersection threshold. Regarding the quantification of severity, an average level of 38.9% was reached, with a significant low difference with the core systems and software tested compared to Tukey test at 5% probability, considering visual acuity as of a diagrammatic scale.

key-words: deep learning. object detection. computer vision. entomology. phytopathology.


Funcionamento e Exemplo da Aplicação

Funcionamento

Exemplo

Repositório do Aplicativo

  • https://github.com/Lucs1590/Coffee_Recognize

Repositório da API

  • https://github.com/AlvaroCavalcante/CoffeeRecognizeAPI

Owner

  • Name: Lucas de Brito Silva
  • Login: Lucs1590
  • Kind: user
  • Location: Indaiatuba, São Paulo, Brazil
  • Company: Agibank

| Machine Learning Engineer at Agi | MSc. Computer Science

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Coffe Recognition
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: ÁLVARO LEANDRO
    family-names: CAVALCANTE CARNEIRO
    affiliation: FATEC Pompéia “Shunji Nishimura”
    orcid: 'https://orcid.org/0000-0002-9485-7229'
    email: Leandro0807@live.com
  - given-names: LUCAS
    name-particle: DE
    family-names: BRITO SILVA
    email: lucasbsilva29@gmail.com
    affiliation: FATEC Pompéia “Shunji Nishimura”
    orcid: 'https://orcid.org/0000-0001-6748-5100'
  - given-names: MARISA
    family-names: SILVEIRA ALMEIDA RENAUD FAULIN
    email: marisa.faulin@fatec.sp.gov.br
    affiliation: FATEC Pompéia “Shunji Nishimura”
  - given-names: JOÃO RICARDO
    family-names: FAVAN
    email: joao.favan@fatecpompeia.edu.br
    affiliation: FATEC Pompéia “Shunji Nishimura”
identifiers:
  - type: url
    value: 'https://arxiv.org/abs/2103.11241'
    description: Arxiv
  - type: other
    value: 'https://github.com/Lucs1590/Coffee_Recognize'
    description: App Repository
  - type: other
    value: API Repository
    description: >-
      https://github.com/AlvaroCavalcante/Coffee_Recognize_API
repository-code: >-
  https://github.com/Lucs1590/coffee-phytopathology-detection
repository: 'https://github.com/AlvaroCavalcante/Coffee_Recognize_API'
abstract: >-
  Pest and disease control play a key role in agriculture,
  millions of dollars are spent annually due to the damage
  caused by these agents. However, several advances are
  being made in the areas of computer vision and deep
  learning, due to the creation of new algorithms and the
  increased processing power of modern computers. Based on
  this assumption, the aim of this research was to I) create
  an algorithm capable of identifying and locating different
  phytosanitary problems in coffee leaves (Coffea arabica)
  and II) quantifying the severity of coffee leaf rust.
  Different convolutional neural network architectures,
  Python programming language, OpenCV library and k-means
  algorithm were used. The results show an average accuracy
  of 81% in the classification and localization of the
  leaves phytosanitary, considering 50% of union over
  intersection threshold. Regarding the quantification of
  severity, an average level of 38.9% was reached, with a
  significant low difference with the core systems and
  software tested compared to Tukey test at 5% probability,
  considering visual acuity as of a diagrammatic scale.
keywords:
  - deep learning
  - object detection
  - computer vision
  - entomology
  - phytopathology
license: GPL-3.0+

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels