Sistema de classificação de plantas por meio de suas folhas usando uma arquitetura híbrida composta por algoritmos genéticos e rede neural artificial

• Ano de defesa: 2013
• Autor(a) principal: Borges, Thiago Henrique
• Orientador(a): Carrijo, Gilberto Arantes
• Banca de defesa: Flores, Edna Lúcia , Veiga, Antônio Cláudio Paschoarelli , Arruda, Benedito Alencar de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia
• Programa de Pós-Graduação: Programa de Pós-graduação em Engenharia Elétrica
• Departamento: Engenharias
• País: BR
• Palavras-chave em Português: Reconhecimento de padrões; Reconhecimento de plantas; Algoritmos genéticos; Redes neurais artificiais; Plantas - Identificação; Redes neurais (Computação)
• Palavras-chave em Inglês: Patterns recognition; Plants recognition; Genetic algorithms; Articial neural network
• Área do conhecimento CNPq: CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://repositorio.ufu.br/handle/123456789/14538; https://doi.org/10.14393/ufu.di.2013.232

The number of plants at risk of extinction has increased gradually. With the purpose of reducing the risk is necessary identify the species for planning protection methods. The biodiversity of species existing in the plant kingdom make the use of traditional models of recognition and taxonomy a process very complex and slow. The identification of a plant can be performed observing his features, such as: fruits, seeds, flowers, roots, leaves and stems. But the simplest feature used are the leaves.This paper presents a hybrid system for identifying plant based on leaf image. This system is composed by Genetic Algorithm (GA) and Artificial Neural Network (ANN). The role played by the GA is to perform a preselection of plants forming a group that the answer of an unknown leaf is more probable and the purpose of ANN, trained by backpropagation algorithm, is to classify the unknown leaf performing the search only in the group calculated by the AG. Several tests were conducted and the results obtained demonstrate that the hybrid system achieved a recognition rate of 93,2%.