Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks

Bambil, Deborah; Pistori, Hemerson; Bao, Francielli; Weber, Vanessa; Alves, Flávio Macêdo; Gonçalves, Eduardo G.; Figueiredo, Lúcio Flávio de Alencar; Abreu, U. G. P. de; Arruda, Rafael; Bortolotto, Ieda Maria

doi:10.1007/s10669-020-09769-w

Cited by 37 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We used a method that has been successful in classifying biological data, performed to classify leaves and pollens. In this experiment, the deep learning network obtained a result very close to SVM, in which both performed better (Bambil et al 2020). Comparing different classification techniques makes it possible to reduce the issues surrounding algorithm choice in the classification of features (Wen et al 2015).…”

mentioning

confidence: 64%

“…The algorithm classification allows one to verify which has the best performance of classification and, thus, to analyse and evaluate the best method for solving problems (Bambil et al 2020). The use of different algorithms is necessary for information extraction and seed classification, as these algorithms address morphological aspects such as shape (Granitto et al 2005), colour and texture (Granitto et al 2002), as well as size (Granitto et al 2003), aspects that are adequate for the classification of different types of seeds (Wäldchen et al 2018).…”

mentioning

confidence: 99%

“…The percentage of correct classification (PCC) was used to analyse the results (e.g., Bambil et al 2020). The results of the general percentage of the algorithm's classification of all trained classes and ROC area are characterized by the weighted average of precision and recall (Amarnath et al 2018).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Applicability of computer vision in seed identification: deep learning, random forest, and support vector machine classification algorithms

Bao

Bambil

2021

Acta Bot. Bras.

Self Cite

View full text Add to dashboard Cite

The use of computer image analysis can assist the extraction of morphological information from seeds, potentially serving as a resource for solving taxonomic problems that require extensive training by specialists whose primary method of examination is visual identification. We propose to test the ability of deep learning, SVM and random forest algorithms to classify seeds from twelve species of aquatic plants as an alternative to traditional classification methods. A total of 150 seeds of the species were collected. The attributes of colour, shape, and texture were analysed through the machine learning algorithms of deep learning, random forest, and support vector machine (SVM). Computer vision proved to be efficient at classifying species using all three algorithms, with an accuracy rate for SVM of 97.91 %, random forest 97.08 % and deep learning 92.5 %. We believe that the method performed well in our experiment and improved seed classification accuracy. As a result, the algorithms SVM and random forest were found to be enough at aquatic plant seed recognition.

show abstract

mentioning

confidence: 64%

mentioning

confidence: 99%

See 1 more Smart Citation

Applicability of computer vision in seed identification: deep learning, random forest, and support vector machine classification algorithms

Bao

Bambil

2021

Acta Bot. Bras.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As imagens obtidas do dataset ISIC foram processadas em 2 (dois) momentos: inicialmente para a classificação com o algoritmo HGBC elas foram submetidas ao extrator de características desenvolvido por um dos autores desse trabalho e disponível na plataforma FAON_MLP. O atual extrator extrai 785 atributos que envolvem características estatísticas de primeira ordem (histograma e forma), textura, padrão binário local, momentos de HU, momentos de Zernike, características de Haralik e informações do valor mínimo, máximo, média e desvio padrão para cada canal de cor vermelho/verde/azul (RGB, do inglês red/green/blue), tonalidade/saturação/brilho (HSV, do inglês hue/saturation/value) e CIELab [12]. Após analisar e verificar que alguns dos atributos produzidos são constantes, os mesmos são descartados, restando um arquivo de valores separados por vírgula (CSV, do inglês commaseparated values) de entrada com 631 atributos.…”

Section: B Extração De Característicasunclassified

Aprendizado de máquina aplicado ao diagnóstico de câncer de pele

Silva¹,

Souza²,

Bambil³

et al. 2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

Self Cite

View full text Add to dashboard Cite

Na última década, as imagens médicas têm demonstrado relevante papel no diagnóstico precoce de câncer de pele, notadamente, com o advento das tecnologias de inteligência artificial que aprendem a diferenciar classes de imagens com base em imagens pré-classificadas, como por exemplo, aquelas obtidas em bancos de imagens médicas contendo lesões cutâneas classificadas como malignas ou benignas. Neste estudo apresentamos os resultados de identificação e classificação de lesões de pele quanto à malignidade usando uma plataforma de aprendizado de máquina desenvolvida em nosso laboratório — a “FAON_Machine_Learning_Platform (FAON_MLP)” — e as redes neurais convolucionais pré-treinadas ResNet 152 V2, VGG16, VGG19 e AlexNet. Para a avaliação de desempenho dos algoritmos segundo métricas objetivas, se usou um banco de dados público com imagens contendo lesões de pele classificadas como benignas ou malignas. Para ser mais preciso, o banco de dados de imagens possui 1800 imagens diagnosticadas com benignas e 1497 imagens diagnosticadas como malignas. São apresentados os resultados de desempenho dos diversos algoritmos. É discutida também uma avaliação comparativa entre as técnicas utilizadas e com outras técnicas reportadas na literatura. Os resultados se mostraram promissores na diferenciação entre lesões benignas e malignas, com grande potencial para auxiliar profissionais da área da saúde no diagnóstico precoce de câncer de pele, evitando os desdobramentos da sua não ocorrência, como procedimentos cirúrgicos, metástases e até mesmo óbito.

show abstract

“…They compared the performance of deep learning algorithms to other machine learning techniques, and discussed the strengths and weaknesses of each. Bambil et al (2020) compared deep learning to other machine learning techniques, with an application of identification of plant species from images of leaves. The authors further compared image capture methods including scanners and mobile phone cameras, finding that the algorithms performed similarly in each case.…”

mentioning

confidence: 99%

Analytics and decision-making to inform public policy in response to diverse threats

2020

View full text Add to dashboard Cite

Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks

Cited by 37 publications

References 18 publications

Applicability of computer vision in seed identification: deep learning, random forest, and support vector machine classification algorithms

Applicability of computer vision in seed identification: deep learning, random forest, and support vector machine classification algorithms

Aprendizado de máquina aplicado ao diagnóstico de câncer de pele

Analytics and decision-making to inform public policy in response to diverse threats

Contact Info

Product

Resources

About