Use este identificador para citar ou linkar para este item: http://rima.ufrrj.br/jspui/handle/20.500.14407/25821
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorCarvalho, João Célio Luna de-
dc.date.accessioned2026-07-20T12:36:14Z-
dc.date.available2026-07-20T12:36:14Z-
dc.date.issued2025-07-29-
dc.identifier.citationCARVALHO, João Célio Luna de. Desenvolvimento de sistema de visão computacional para seleção de produtos agrícolas a partir da aplicação de redes neurais convolucionais. 2025. 99 f. Dissertação (Mestrado em Engenharia Agrícola e Ambiental) - Instituto de Tecnologia, Universidade Federal Rural do Rio de Janeiro, Seropédica, 2025.pt_BR
dc.identifier.urihttp://rima.ufrrj.br/jspui/handle/20.500.14407/25821-
dc.description.abstractA demanda por produtos agrícolas de qualidade aumenta conforme o crescimento da produção alimentícia e da população mundial. Equipamentos focados na classificação destes produtos ainda são escassos e as Redes Neurais Convolucionais (CNN) têm sido aplicadas com este propósito. O objetivo desse projeto foi criar um sistema de visão computacional capaz de selecionar produtos agrícolas de forma automatizada em função de atributos de qualidade. Para isso, a câmara seletora de imagens foi composta por um Raspberry Pi 5 acoplado ao módulo de câmera próprio, monitor LCD e lâmpadas LED para iluminação, com o software para treinamento das CNNs e classificação dos dados armazenados em sua memória interna. Três CNN foram comparadas, sendo duas com arquiteturas pré-estabelecidas (AlexNet e Mobile Net), e uma com arquitetura adaptada para este projeto (OakMoonNet). Um software foi desenvolvido para aquisição das imagens, e outro para a aplicação das CNNs e obtenção das métricas de desempenho de classificação. As CNNs foram aplicadas a seis bancos de imagens, dos quais, dois compostos por imagens obtidas por meio da câmara seletora, com iluminação controlada, e quatro compostos por imagens em condições variadas de ambiente, quantidade e iluminação. A comparação de desempenho das CNNs foi realizada por meio da avaliação dos parâmetros de Acurácia, Precisão, Sensibilidade (Recall) e F1-Score, obtidos durante o treinamento. A CCN OakMoonNet apresentou o melhor desempenho para os experimentos realizados como avaliação da câmara seletora, obtendo 77% de acurácia (tempo de processamento 23 min e 53 seg) para a classificação da severidade de danos em laranjas e 100% de acurácia para classificação dos frutos de tomates em função maturação (tempo de processamento 4 min e 12 seg). Para os experimentos complementares de validação do software, com dados obtidos fora da câmara seletora, o padrão se repetiu, com a OakMoonNet apresentando sempre a maior acurácia e menor tempo de treinamento, se mostrando mais eficiente na classificação de produtos agrícolas em comparação com as CNNs AlexNet e MobileNet, com baixo custo computacional, alta acurácia e baixo tempo de treinamento.pt_BR
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESpt_BR
dc.languageporpt_BR
dc.publisherUniversidade Federal Rural do Rio de Janeiropt_BR
dc.subjectimagens digitaispt_BR
dc.subjectaprendizado de máquinaspt_BR
dc.subjectRaspberry Pipt_BR
dc.subjectpós-colheitapt_BR
dc.subjectdigital imagespt_BR
dc.subjectmachine learningpt_BR
dc.subjectpost-harvestpt_BR
dc.titleDesenvolvimento de sistema de visão computacional para seleção de produtos agrícolas a partir da aplicação de redes neurais convolucionaispt_BR
dc.title.alternativeDevelopment of a computer vision system for selecting agricultural products using convolutional neural networksen
dc.typeDissertaçãopt_BR
dc.description.abstractOtherThe demand for quality agricultural products increases as food production and the world population grows. Equipment focused on the classification of these products is still scarce, and Convolutional Neural Networks (CNN) have been applied for this purpose. The objective of this project was to create a computer vision system capable of automatically selecting agricultural products based on quality attributes. To this end, the image selection camera consisted of a Raspberry Pi 5 coupled with its own camera module, LCD monitor, and LED lamps for lighting, with software for training CNNs and classifying the data stored in its internal memory. Three CNNs were compared, two with pre-established architectures (AlexNet and Mobile Net), and one with an architecture adapted for this project (OakMoonNet). One software was developed for image acquisition, and another for applying CNNs and obtaining classification performance metrics. The CNNs were applied to six image databases, two of which consisted of images obtained using a selector camera with controlled lighting, and four of which consisted of images under varying environmental conditions, quantities, and lighting. The performance of the CNNs was compared by evaluating the parameters of Accuracy, Precision, Sensitivity (Recall), and F1-Score obtained during training. The OakMoonNet CCN performed best in the experiments conducted to evaluate the sorting camera, achieving 77% accuracy (processing time 23 min and 53 sec) for classifying the severity of damage to oranges and 100% accuracy for classifying tomatoes according to ripeness (processing time 4 min and 12 sec). For the complementary software validation experiments, with data obtained outside the sorting chamber, the pattern was repeated, with OakMoonNet always showing the highest accuracy and shortest training time, proving to be more efficient in the classification of agricultural products compared to AlexNet and MobileNet CNNs, with low computational cost, high accuracy, and short training time.en
dc.contributor.advisor1Costa, Anderson Gomide-
dc.contributor.advisor1IDhttps://orcid.org/0000-0003-0594-8514pt_BR
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/6959807888629144pt_BR
dc.contributor.advisor-co1Oliveira, Marcus Vinicius Morais de-
dc.contributor.advisor-co1IDhttps://orcid.org/0000-0002-8568-5568pt_BR
dc.contributor.advisor-co1Latteshttp://lattes.cnpq.br/6164315892344545pt_BR
dc.contributor.referee1Costa, Anderson Gomide-
dc.contributor.referee1IDhttps://orcid.org/0000-0003-0594-8514pt_BR
dc.contributor.referee1Latteshttp://lattes.cnpq.br/6959807888629144pt_BR
dc.contributor.referee2Paes, Juliana Lobo-
dc.contributor.referee2IDhttps://orcid.org/0000-0001-9301-0547pt_BR
dc.contributor.referee2Latteshttp://lattes.cnpq.br/8567579362150921pt_BR
dc.contributor.referee3Sousa, Emanoel Di Tarso Dos Santos-
dc.creator.IDhttps://orcid.org/0000-0003-1676-4577pt_BR
dc.creator.Latteshttp://lattes.cnpq.br/7788533101686922pt_BR
dc.publisher.countryBrasilpt_BR
dc.publisher.departmentInstituto de Tecnologiapt_BR
dc.publisher.initialsUFRRJpt_BR
dc.publisher.programPrograma de Pós-Graduação em Engenharia Agrícola e Ambientalpt_BR
dc.relation.referencesABEKOON, T.; SAJINDRA, H.; JAYAKODY, J. A. D. C. A.; SAMARAKOON, E. R. J.; RATHNAYAKE, U. Image processing techniques to identify tomato quality under market conditions. Smart Agricultural Technology, v. 7, n. 100433, p. 100433, 2024. ISSN 2772- 3755. DOI: 10.1016/j.atech.2024.100433. Disponível em: https://www.sciencedirect.com/science/article/pii/S2772375524000388?via%3Dihub. Acesso em: 10 abr. 2025. ALI, M.; VLASKAMP, J. H. A.; NASSER EDDINY, N.; FALCONER, B.; ORAM, C. Technical development and socioeconomic implications of the Raspberry Pi as a learning tool in developing countries. In: COMPUTER SCIENCE AND ELECTRONIC ENGINEERING CONFERENCE, 5., 2013, Colchester. Anais [...]. Colchester: IEEE, 2013. p. 103–108 ALOMAR, K.; AYSEL, H. I.; CAI, X. Data Augmentation in Classification and Segmentation: A Survey and New Strategies. Journal of Imaging, v. 9, n. 2, p. 46, 2023. DOI: 10.3390/jimaging9020046. Disponível em: https://www.mdpi.com/2313-433X/9/2/46. Acesso em: 20 set. 2025. ALZUBAIDI, L.; ZHANG, J.; HUMAIDI, A. J.; AL-DUJAILI, A.; DUAN, Y.; AL- SHAMMA, O.; SANTAMARÍA, J.; FADHEL, M. A.; AL-AMIDIE, M.; FARHAN, L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, v. 8, n. 1, p. 1–74, 2021. ISSN 2196-1115. DOI: 10.1186/s40537-021- 00444-8. Disponível em: https://journalofbigdata.springeropen.com/articles/10.1186/s40537- 021-00444-8. Acesso em: 07 out. 2023. ASRINY, D. M.; RANI, S.; HIDAYATULLAH, A. F. Orange fruit images classification using convolutional neural networks. IOP Conference Series: Materials Science and Engineering, v. 803, n. 1, p. 012020, 2020. Trabalho apresentado no IOP Conference Series: Materials Science and Engineering, 2020, Yogyakarta. BASFORD, P. J.; JOHNSTON, S. J.; PERKINS, C. S.; GARNOCK-JONES, T.; TSO, F. P.; PEZAROS, D.; MULLINS, R. D.; YONEKI, E.; SINGER, J.; COX, S. J. Performance analysis 87 of single board computer clusters. Future Generation Computer Systems, v. 102, p. 278–291, 2020. DOI: 10.1016/j.future.2019.07.040. Disponível em: https://www.sciencedirect.com/science/article/pii/S0167739X1833142X. Acesso em: 31 ago. 2025. BRAGA, R. A., Jr; CONTADO, J. L.; DUCATTI, K. R.; SILVA, E. A. A. Analysis of seed vigor using the biospeckle laser technique. AgriEngineering, v. 7, n. 1, p. 3, 2024. ISSN 2624- 7402. DOI: 10.3390/agriengineering7010003. Disponível em: https://www.mdpi.com/2624- 7402/7/1/3. Acesso em: 05 mar. 2025. BRIGATO, L.; IOCCHI, L. A close look at deep learning with small data. Proceedings of the International Conference on Pattern Recognition, Milan, p. 2490–2497, 2021. Supl. 1. Trabalho apresentado no 25o International Conference on Pattern Recognition, 2020, Milan. CEAGESP – Centro de Qualidade em Horticultura. Classificação do tomate. São Paulo: ABH, 2003. Disponível em: https://ceagesp.gov.br/wp-content/uploads/2015/07/tomate.pdf. Acesso em: 05 out. 2023. CEAGESP – Companhia de Entrepostos e Armazéns Gerais de São Paulo. Normas para classificação de citros de mesa. São Paulo: CEAGESP, 2011. 12 p. Disponível em: https://ceagesp.gov.br/wp-content/uploads/2015/07/citros.pdf. Acesso em: 05 out. 2023. CHAKRABORTY, S. K.; SUBEESH, A.; DUBEY, K.; JAT, D.; CHANDEL, N. S.; POTDAR, R.; RAO, N. R. N. V. G.; KUMAR, D. Development of an optimally designed real-time automatic citrus fruit grading–sorting machine leveraging computer vision-based adaptive deep learning model. Engineering Applications of Artificial Intelligence, v. 120, n. 105826, p. 105826, 2023. DOI: 10.1016/j.engappai.2023.105826. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0952197623000106?via%3Dihub. Acesso em: 15 out. 2023. CHATURVEDI, A.; SHARMA, S.; JANGHEL, R. R. Detection of external defects in tomatoes using deep learning. Journal of Ambient Intelligence and Humanized Computing, v. 14, n. 88 3, p. 2709–2721, 2023. DOI: 10.1007/s12652-023-04514-y. Disponível em: https://link.springer.com/article/10.1007/s12652-023-04514-y. Acesso em: 18 nov. 2024. CHEN, W.; LU, S.; LIU, B.; LI, G.; QIAN, T. Detecting citrus in orchard environment by using improved YOLOv4. Scientific Programming, v. 2020, p. 1–13, 2020. DOI: 10.1155/2020/8859237. Disponível em: https://onlinelibrary.wiley.com/doi/10.1155/2020/8859237. Acesso em: 09 jan. 2025. COSTA, A. G.; BRAGA Jr., R. A.; VILAS BOAS, E. V. B.; RISSO, M. Early prediction of internal bruising in potatoes by biospeckle laser technique. African Journal of Agricultural Research, v. 13, n. 14, p. 691–697, 2018. DOI: 10.5897/AJAR2017.12959. Disponível em: https://academicjournals.org/journal/AJAR/article-abstract/6C3128356571. Acesso em: 20 mar. 2025 CUI, M.; JIANG, Q.; LI, N.; XUE, X. Research on strawberry maturity detection technology based on improved YOLOv4. Journal of Physics: Conference Series, v. 2138, n. 1, p. 012012, 2021. DOI: 10.1088/1742-6596/2138/1/012012. Disponível em: https://iopscience.iop.org/article/10.1088/1742-6596/2138/1/012012. Acesso em: 18 nov. 2023. DAS, P.; YADAV, J. P. S. Automated tomato maturity grading system using CNN. Proceedings of the International Conference on Smart Electronics and Communication, Tirunelveli, p. 136–142, 2020. Trabalho apresentado no 2020 International Conference on Smart Electronics and Communication (ICOSEC), 2020, Tirunelveli. DE LUNA, R. G.; DADIOS, E. P.; BANDALA, A. A.; VICERRA, R. R. P. Tomato fruit image dataset for deep transfer learning-based defect detection. Proceedings of the IEEE International Conference on Cybernetics and Intelligent Systems and Robotics, Automation and Mechatronics, Singapore, p. 356–361, 2020. Trabalho apresentado no 2019 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM), 2019, Singapore. 89 ELARABY, A.; HAMDY, W.; ALANAZI, S. Classification of citrus diseases using optimization deep learning approach. Computational Intelligence and Neuroscience, v. 2022, p. 9153207, 2022. DOI: 10.1155/2022/9153207. Disponível em: https://onlinelibrary.wiley.com/doi/10.1155/2022/9153207. Acesso em: 09 jan. 2025. ERLINA, T.; FIKRI, M. Y. Yolo Algorithm-Based Visitor Detection System for Small Retail Stores Using Single Board Computer. J. Appl. Eng. Technol. Sci, v. 4, n. 2, p. 908–920, 2023. DOI: 10.37385/jaets.v4i2.1872. Disponível em: https://journal.yrpipku.com/index.php/jaets/article/view/1872. Acesso em: 31 ago. 2025. FANG, W.; LOVE, P. E. D.; LUO, H.; DING, L. Computer vision for behaviour-based safety in construction: A review and future directions. Advanced Engineering Informatics, v. 43, n. 100980, p. 100980, 2020. DOI: 10.1016/j.aei.2019.100980. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S1474034619305531?via%3Dihub. Acesso em: 20 set. 2023. FENG, J.; WANG, Z.; WANG, S.; TIAN, S.; XU, H. MSDD-YOLOX: An enhanced YOLOX for real-time surface defect detection of oranges by type. European Journal of Agronomy: The Journal of the European Society for Agronomy, v. 149, n. 126918, p. 126918, 2023. DOI: 10.1016/j.eja.2023.126918. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S1161030123001867?via%3Dihub. Acesso em: 09 jan. 2025. GONZALEZ-HUITRON, V.; LEÓN-BORGES, J. A.; RODRIGUEZ-MATA, A. E.; AMABILIS-SOSA, L. E.; RAMÍREZ-PEREDA, B.; RODRIGUEZ, H. Disease detection in tomato leaves via CNN with lightweight architectures implemented in Raspberry Pi 4. Computers and Electronics in Agriculture, v. 181, p. 105951, 2021. DOI: 10.1016/j.compag.2020.105951. Disponível em: https://www.sciencedirect.com/science/article/pii/S0168169920331562. Acesso em: 31 ago. 2025. GOODMAN, J. W. Statistical properties of laser speckle patterns. In: DAINTY, J. C. (ed.). Laser speckle and related phenomena. Berlin Heidelberg: Springer-Verlag, 1975. p. 9–75. 90 Disponível em: https://link.springer.com/content/pdf/10.1007/978-3-662-43205-1_2.pdf. Acesso em: 10 mar. 2025. GOYAL, K.; KUMAR, P.; VERMA, K. AI-based fruit identification and quality detection system. Multimedia Tools and Applications, v. 82, n. 16, p. 24573–24604, 2023. DOI: 10.1007/s11042-022-14188-x. Disponível em: https://link.springer.com/article/10.1007/s11042-022-14188-x. Acesso em: 15 abr. 2024. GRIGORIEV, S. N.; MARTINOV, G. M. An ARM-based multi-channel CNC solution for multi-tasking turning and milling machines. Procedia CIRP, v. 46, p. 525–528, 2016. DOI: 10.1016/j.procir.2016.04.036. Disponível em: https://www.sciencedirect.com/science/article/pii/S2212827116301913. Acesso em: 31 ago. 2025. GU, J.; WANG, Z.; KUEN, J.; MA, L.; SHAHROUDY, A.; SHUAI, B.; LIU, T.; WANG, X.; WANG, G.; CAI, J.; CHEN, T. Recent advances in convolutional neural networks. Pattern Recognition, v. 77, p. 354–377, 2018. DOI: 10.1016/j.patcog.2017.10.013. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0031320317304120?via%3Dihub. Acesso em: 13 jan. 2024. HABARAGAMUWA, H.; OGAWA, Y.; SUZUKI, T.; SHIIGI, T.; ONO, M.; KONDO, N. Detecting greenhouse strawberries (mature and immature), using deep convolutional neural network. Engineering in Agriculture, Environment and Food, v. 11, n. 3, p. 127–138, 2018. DOI: 10.1016/j.eaef.2018.03.001. Disponível em: https://www.jstage.jst.go.jp/article/eaef/11/3/11_127/_article/-char/en. Acesso em: 10 nov. 2023. HADIPOUR-ROKNI, R.; ASKARI ASLI-ARDEH, E.; JAHANBAKHSHI, A.; ESMAEILI- AFKAROTI, I.; SABZI, S. Intelligent detection of citrus fruit pests using machine vision system and convolutional neural network through transfer learning technique. Computers in Biology and Medicine, v. 155, n. 106611, p. 106611, 2023. DOI: 10.1016/j.compbiomed.2023.106611. Disponível em: 91 https://www.sciencedirect.com/science/article/abs/pii/S0010482523000768?via%3Dihub. Acesso em: 09 jan. 2025. HARDKERNEL CO. LTD. ODROID—GO SUPER. Hardkernel Co. Ltd., 2021. Disponível em: https://www.hardkernel.com. Acesso em: 31 ago. 2025 HENDRAWAN, Y.; ROHMATULLOH, B.; PRAKOSO, I.; LIANA, V.; FAUZY, M. R.; DAMAYANTI, R.; HERMANTO, M. B.; AL RIZA, D. F.; SANDRA. Classification of large green chilli maturity using deep learning. IOP Conference Series: Earth and Environmental Science, v. 924, n. 1, p. 012009, 2021. DOI: 10.1088/1755-1315/924/1/012009. Disponível em: https://iopscience.iop.org/article/10.1088/1755-1315/924/1/012009. Acesso em: 10 out. 2023. HOWARD, A. G.; ZHU, M.; CHEN, B.; KALENICHENKO, D.; WANG, W.; WEYAND, T.; ANDREETTO, M.; ADAM, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017. Disponível em: https://arxiv.org/abs/1704.04861. Acesso em: 15 set. 2023. HU, C.; LIU, X.; PAN, Z.; LI, P. Automatic detection of single ripe tomato on plant combining faster R-CNN and intuitionistic fuzzy set. IEEE Access: Practical Innovations, Open Solutions, v. 7, p. 154683–154696, 2019. DOI: 10.1109/ACCESS.2019.2949343. Disponível em: https://ieeexplore.ieee.org/document/8882212. Acesso em: 03 dez. 2024. HU, D.; JIA, T.; SUN, X.; ZHOU, T.; HUANG, Y.; SUN, Z.; ZHANG, C.; SUN, T.; ZHOU, G. Applications of optical property measurement for quality evaluation of agri-food products: a review. Critical Reviews in Food Science and Nutrition, v. 64, n. 33, p. 12599–12619, 2024. DOI: 10.1080/10408398.2023.225526. Disponível em: https://www.tandfonline.com/doi/full/10.1080/10408398.2023.2255260. Acesso em: 09 jan. 2024. HUANG, Y.-P.; WANG, T.-H.; BASANTA, H. Using fuzzy mask R-CNN model to automatically identify tomato ripeness. IEEE Access: Practical Innovations, Open Solutions, 92 v. 8, p. 207672–207682, 2020. DOI: 10.1109/ACCESS.2020.3038184. Disponível em: https://ieeexplore.ieee.org/document/9260129. Acesso em: 18 nov. 2024. HUBEL, D. H.; WIESEL, T. N. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal of Physiology, v. 160, n. 1, p. 106–154, 1962. DOI: 10.1113/jphysiol.1962.sp006837. Disponível em: https://physoc.onlinelibrary.wiley.com/doi/10.1113/jphysiol.1962.sp006837. Acesso em: 06 out. 2023. IBGE – Instituto Brasileiro de Geografia e Estatística. Estatística Mensal da Produção Agrícola. Levantamento Sistemático da Produção agrícola. 2024. Disponível em: https://www.ibge.gov.br/estatisticas/economicas/agricultura-e-pecuaria/9201-levantamento- sistematico-da-producao-agricola.html. Acesso em: 15 fev. 2024 IOFFE, S.; SZEGEDY, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, p. 448–456, 2015. Trabalho apresentado no International Conference on Machine Learning, 2015, Lille. KAISER, L.; GOMEZ, A. N.; CHOLLET, F. Depthwise separable convolutions for neural machine translation. arXiv preprint arXiv:1706.03059, 2017. Disponível em: https://arxiv.org/abs/1706.03059. Acesso em: 04 fev. 2024. KALER, N.; BHATIA, V.; MISHRA, A. K. Deep learning-based robust analysis of laser bio- speckle data for detection of fungal-infected soybean seeds. IEEE Access: Practical Innovations, Open Solutions, v. 11, p. 89331–89348, 2023. DOI: 10.1109/ACCESS.2023.3305273. Disponível em: https://ieeexplore.ieee.org/document/10216973. Acesso em: 13 mar. 2025. KHAN, M. R. Advances in architectures for deep learning: A thorough examination of present trends. Journal of Artificial Intelligence General Science, v. 1, n. 1, p. 24–30, 2024. DOI: 10.60087/jaigs.v1i1.p30. Disponível em: https://jaigs.org/index.php/JAIGS/article/view/14. Acesso em: 03 mai. 2025. 93 KHATUN, T.; RAZZAK, A.; ISLAM, M. S.; UDDIN, M. S. et al. An extensive real-world in field tomato image dataset involving maturity classification and recognition of fresh and defect tomatoes. Data in Brief, v. 51, n. 109688, p. 109688, 2023. DOI: 10.1016/j.dib.2023.109688. Disponível em: https://pubmed.ncbi.nlm.nih.gov/37920387/. Acesso em: 03 nov. 2024. KHATUN, M.; ALI, M. F.; TURZO, N. A.; NINE, J.; SARKER, P. Fruits classification using convolutional neural network. GRD Journals – Global Research and Development Journal for Engineering, v. 5, n. 8, p. 1–6, 2020. DOI: 10.13140/RG.2.2.16997.22244. Disponível em: https://www.academia.edu/download/64177538/GRDJEV05I080015.pdf. Acesso em: 18 nov. 2024. KOPILER, A. A.; SILVA, V. N. A. L. da; OLIVEIRA, L. A. A. de; LINDEN, R.; SILVA, L. R. A. de A.; FONSECA, B. L. da C. Redes Neurais Artificiais e suas aplicações no setor elétrico. Revista de Engenharias da Faculdade Salesiana, v. 1, n. 9, p. 27–33, 2019. Disponível em: https://www.fsma.edu.br/RESA/Edicao9/FSMA_RESA_2019_1_04.pdf. Acesso em: 07 set 2023. KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, v. 60, n. 6, p. 84–90, 2017. DOI: 10.1145/3065386. Disponível em: https://dl.acm.org/doi/10.1145/3065386. Acesso em: 02 fev. 2024. KUKREJA, V.; DHIMAN, P. A deep neural network based disease detection scheme for citrus fruits. Proceedings of the International Conference on Smart Electronics and Communication, Tirunelveli, p. 97–101, 2020. Trabalho apresentado no 2020 International Conference on Smart Electronics and Communication (ICOSEC), 2020, Tirunelveli. KUMAR, A.; JOSHI, R. C., DUTTA, M. K., JONAK, M. BURGET, R. Fruit-CNN: An efficient deep learning-based fruit classification and quality assessment for precision agriculture. Proceedings of the International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, Moscow, p. 60–65, 2021. 94 Trabalho apresentado no 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 2021, Moscow. LI, G.; ZHANG, M.; LI, J.; LV, F.; TONG, G. Efficient densely connected convolutional neural networks. Pattern Recognition, v. 109, n. 107610, p. 107610, 2021. DOI: 10.1016/j.patcog.2020.107610. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0031320320304131?via%3Dihub. Acesso em: 08 out. 2023. LIMA, A. F.; SILVA, E. G. DE A.; IWATA, B. DE F. Agriculturas e agricultura familiar no Brasil: uma revisão de literatura. Retratos de Assentamentos, v. 22, n. 1, p. 50–68, 2019. DOI: 10.25059/2527-2594/retratosdeassentamentos/2019.v22i1.332. Disponível em: https://retratosdeassentamentos.com/index.php/retratos/article/view/332. Acesso em: 12 out. 2023. LINDNER, T.; WYRWAŁ, D.; BIAŁEK, M.; NOWAK, P. Face recognition system based on a single-board computer. In: INTERNATIONAL CONFERENCE MECHATRONIC SYSTEMS AND MATERIALS, 2020, Opole. Anais [...]. Opole: IEEE, 2020. p. 1–6 LU, J.; CHEN, W.; LAN, Y.; QIU, X.; HUANG, J.; LUO, H. Design of citrus peel defect and fruit morphology detection method based on machine vision. Computers and Electronics in Agriculture, v. 219, n. 108721, p. 108721, 2024. DOI: 10.1016/j.compag.2024.108721. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0168169924001121?via%3Dihub. Acesso em: 09 jan. 2025. MCCULLOCH, W. S.; PITTS, W. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, v. 5, n. 4, p. 115–133, 1943. DOI: 10.1007/BF02478259. Disponível em: https://link.springer.com/article/10.1007/BF02478259. Acesso em: 04 set. 2023. MINSKY, M.; PAPERT, S. An introduction to computational geometry. Cambridge: TIASS, HIT, v. 479, n. 480, p. 104, 1969. 95 MUNDIM FILHO, A. C.; ALVARENGA, C.; CARNEIRO, M. G. Colher ou não colher? Uma rede neural convolucional para apoiar cafeicultores na decisão da colheita. Anais Estendidos do XVII Simpósio Brasileiro de Sistemas de Informação, p. 57–60, 2021. Trabalho apresentado no XVII Simpósio Brasileiro de Sistemas de Informação, 2021, Uberlândia. OLIVEIRA, C. T. de. Monitoramento da maturação dos frutos e de doenças do cafeeiro utilizando modelos de deep learning. Dissertação (Mestrado em Engenharia Agrícola) – Programa de Pós-Graduação em Engenharia Agrícola, Universidade Federal de Viçosa, Viçosa, 2021. OULOMARA, G.; TRIBILLON, J.; DUVERNOY, J. Biological Activity Measurement on Botanical Specimen Surfaces Using a Temporal Decorrelation Effect of Laser Speckle. Journal of Modern Optics, v. 36, n. 2, p. 165–179, 1989. DOI: 10.1080/09500348914550221. Disponível em: https://www.tandfonline.com/doi/abs/10.1080/09500348914550221. Acesso em: 1 out. 2025. PALUMBO, M.; CEFOLA, M.; PACE, B.; ATTOLICO, G.; COLELLI, G. Computer vision system based on conventional imaging for non-destructively evaluating quality attributes in fresh and packaged fruit and vegetables. Postharvest Biology and Technology, v. 200, n. 112332, p. 112332, 2023. DOI: 10.1016/j.postharvbio.2023.112332. Disponível em: https://www.sciencedirect.com/science/article/pii/S0925521423000935?via%3Dihub. Acesso em: 08 set. 2023. PARK, H. S.; AHN, Y. C. Method for measuring blood flow and depth of blood vessel based on laser speckle contrast imaging using 3D convolutional neural network: A preliminary study. Optics & Laser Technology, v. 179, n. 111367, p. 111367, 2024. DOI: 10.1016/j.optlastec.2024.111367. Disponível em: https://www.sciencedirect.com/science/article/pii/S0030399224008259?via%3Dihub. Acesso em: 20 set. 2025. PAVARIN, F. F. A.; FRACAROLLI, J. A.; FALCÃO, A. X. Biospeckle laser for assessing tomatoes ripeness indexes. Revista Ciência Agronômica, v. 55, p. e20207677, 2024. DOI: 96 10.5935/1806-6690.20240022. Disponível em: https://periodicos.ufc.br/revistacienciaagronomica/article/view/91892. Acesso em: 09 mar. 2025. PANDE, A.; MUNOT, M.; SREEEMATHY, R.; BAKARE, R. V. An efficient approach to fruit classification and grading using deep convolutional neural network. In: IEEE 5th International Conference for Convergence in Technology (I2CT), 2019, Pune. Anais [...] Pune: IEEE, 2019. PHAN, Q.-H.; NGUYEN, V.-T.; LIEN, C.-H.; DUONG, T.-P.; HOU, M. T.-K.; LE, N.-B. Classification of tomato fruit using Yolov5 and convolutional neural network models. Plants, v. 12, n. 4, 2023. DOI: 10.3390/plants12040790. Disponível em: https://www.mdpi.com/2223- 7747/12/4/790. Acesso em: 20 mar. 2024. QURESHI, R.; MEHBOOB, S. H.; AAMIR, M. Sustainable green fog computing for smart agriculture. Wireless Personal Communications, v. 121, n. 2, p. 1379–1390, 2021. DOI: 10.1007/s11277-021-09059-x. Disponível em: https://link.springer.com/article/10.1007/s11277-021-09059-x. Acesso em: 31 ago. 2025. RABAL, H. J.; BRAGA JR, R. A. Dynamic laser speckle and applications. Boca Raton, FL: CRC Press, 2018. RAHMAT, H.; WAHJUNI, S.; RAHMAWAN, H. Performance analysis of deep learning- based object detectors on raspberry pi for detecting melon leaf abnormality. Int. J. Adv. Sci. Eng. Inf. Technol., v. 12, n. 2, p. 572–579, 2022. DOI: 10.18517/ijaseit.12.2.13801. Disponível em: https://www.researchgate.net/publication/360294751_Performance_Analysis_of_Deep_Learn ing-based_Object_Detectors_on_Raspberry_Pi_for_Detecting_Melon_Leaf_Abnormality. Acesso em: 31 ago. 2025. RASPBERRY PI FOUNDATION. Raspberry Pi 400. Raspberry Pi Foundation in association with Broadcom, 2021. Disponível em: https://www.raspberrypi.org/. Acesso em: 31 ago. 2025. 97 RAUBER, T. W. Redes neurais artificiais. Universidade Federal do Espírito Santo, 2005. RICHARDSON, M.; WALLACE, S. Getting Started with Raspberry Pi: Electronic Projects with Python, Scratch, and Linux. Sebastopol, CA: Maker Media, Inc., 2014. RUSSEL, S.; NORVIG, P. Artificial intelligence: a modern approach. 4. ed. New Jersey: Prentice Hall, 2020. ROSA, R. P. Método de classificação de pragas por meio de rede neural convolucional profunda. 2018. Dissertação (Mestrado em Computação Aplicada) — Programa de Pós- Graduação em Ciência Aplicada, Universidade Estadual de Ponta Grossa, Ponta Grossa, 2018. ROSENBLATT, F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, v. 65, n. 6, p. 386–408, 1958. DOI: 10.1037/h0042519. Disponível em: https://psycnet.apa.org/doiLanding?doi=10.1037%2Fh0042519. Acesso em: 15 nov. 2023. RUMELHART, D. E.; HINTON, G. E.; WILLIAMS, R. J. Learning internal representations by error propagation. In: MCCLELLAND, J. L.; RUMELHART, D. E. (org.). Parallel distributed processing: explorations in the microstructure of cognition. v. 1. Cambridge, MA: MIT Press, 1985. p. 318–362. SANTOS, D. M. Redes neurais convolucionais para classificar a maturação de frutos de café. 2022. Dissertação (Mestrado em Agricultura e Informações Geoespaciais) — Instituto de Ciências Agrárias, Universidade Federal de Uberlândia, Monte Carmelo, MG, 2022. SHIVASHANKAR, M.; PANDEY, M.; ZAKWAN, M. Estimation of settling velocity using generalized reduced gradient (GRG) and hybrid generalized reduced gradient–genetic algorithm (hybrid GRG-GA). Acta Geophysica, v. 70, n. 5, p. 2487–2497, 2022. DOI: 10.1007/s11600-021-00706-2. Disponível em: https://link.springer.com/article/10.1007/s11600-021-00706-2. Acesso em: 19 out. 2023. 98 TENSORFLOW. Tensorflow. 2024. Disponível em: https://www.tensorflow.org/. Acesso em: 1 abr. 2024. THAKUR, P. S.; KREJCAR, O.; BHATIA, V.; PRAKASH, S. Deep learning based processing framework for spatio-temporal analysis and classification of laser biospeckle data. Optics and Laser Technology, v. 169, n. 110138, p. 110138, 2024. DOI: 10.1016/j.optlastec.2023.110138. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0030399223010319?via%3Dihub. Acesso em: 20 mar. 2025. TSAI, F.-T.; NGUYEN, V.-T.; DUONG, T.-P.; PHAN, Q.-H.; LIEN, C.-H. Tomato fruit detection using modified Yolov5m model with convolutional neural networks. Plants, v. 12, n. 17, 2023. DOI: 10.3390/plants12173067. Disponível em: https://www.mdpi.com/2223- 7747/12/17/3067. Acesso em: 03 jan. 2024. WANG, T.; LU, C.; YANG, M.; HONG, F.; LIU, C. A hybrid method for heartbeat classification via convolutional neural networks, multilayer perceptrons and focal loss. PeerJ Computer Science, v. 6, n. e324, p. e324, 2020. DOI: 10.7717/peerj-cs.324. Disponível em: https://peerj.com/articles/cs-324/. Acesso em: 13 dez. 2023. WANG, Y. X.; RAMANAN, D.; HEBERT, M. Growing a brain: Fine-tuning by increasing model capacity. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, p. 2471–2480, 2017. Trabalho apresentado no IEEE Conference on Computer Vision and Pattern Recognition, 2017, Honolulu. WANG, Z.; LING, Y.; WANG, X.; MENG, D.; NIE, L.; AN, G.; WANG, X. An improved Faster R-CNN model for multi-object tomato maturity detection in complex scenarios. Ecological Informatics, v. 72, n. 101886, p. 101886, 2022. DOI: 10.1016/j.ecoinf.2022.101886. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S1574954122003363?via%3Dihub. Acesso em: 19 ago. 2024. 99 WICHMANN, F. A.; SHARPE, L. T.; GEGENFURTNER, K. R. The contributions of color to recognition memory for natural scenes. Journal of Experimental Psychology: Learning, Memory, and Cognition, v. 28, n. 3, p. 509–520, 2002. DOI: 10.1037/0278-7393.28.3.509. Disponível em: https://psycnet.apa.org/record/2002-12651-010. Acesso em: 14 dez. 2023. XIAO, X.; WANG, Y.; JIANG, Y. Review of research advances in fruit and vegetable harvesting robots. Journal of Electrical Engineering and Technology, v. 19, n. 1, p. 773–789, 2024. DOI: 10.1007/s42835-023-01596-8. Disponível em: https://link.springer.com/article/10.1007/s42835-023-01596-8. Acesso em: 15 out. 2023. WIDROW, B.; HOFF, M. E. Adaptive switching circuits. In: IRE WESCON CONVENTION RECORD, 1960, Los Angeles, CA. p. 96–104. YANG, S.; ZHANG, Z.; LI, J.; WANG, X.; ZHOU, B. Early detection of fungal infection in citrus using biospeckle imaging. Computers and Electronics in Agriculture, v. 225, p. 109293, 2024. DOI: 10.1016/j.compag.2024.109293. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0168169924006847?via%3Dihub. Acesso em: 20 mar. 2025. YAU, H. Learning BeagleBone. Birmingham, UK: Packt Publishing Ltd, 2014. ZDUNEK, A.; KADLEC, K.; BORKOWSKI, A.; LUKASZEWSKA, A. The biospeckle method for the investigation of agricultural crops: A review. Optics and Lasers in Engineering, v. 52, p. 276–285, 2014. DOI: 10.1016/j.optlaseng.2013.06.017. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S0143816613002030?via%3Dihub. Acesso em: 20 mar. 2025. ZU, L.; ZHAO, Y.; LIU, J.; SU, F.; ZHANG, Y.; LIU, P. Detection and segmentation of mature green tomatoes based on mask R-CNN with automatic image acquisition approach. Sensors (Basel, Switzerland), v. 21, n. 23, p. 7842, 2021. DOI: 10.3390/s21237842. Disponível em: https://www.mdpi.com/1424-8220/21/23/7842. Acesso em: 09 out. 2024.pt_BR
dc.subject.cnpqEngenharia Agrícolapt_BR
Aparece nas coleções:Mestrado em Engenharia Agrícola e Ambiental

Se for cadastrado no RIMA, poderá receber informações por email.
Se ainda não tem uma conta, cadastre-se aqui!

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
2025 - João Célio Luna de Carvalho.pdf2,5 MBAdobe PDFAbrir


Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.