Uso de deep learning na classificação de imagens de produtos de um pet shop
Resumo
O Reconhecimento de produtos é uma ferramenta útil para aplicações voltadas à promoção de acessibilidade e à automação de processos. O objetivo deste trabalho foi conseguir classificar produtos especificamente de um pet shop, através do reconhecimento de imagens utilizando técnicas de deep learning. Para o treinamento do modelo, foi necessária a construção de uma base de imagens própria. No total, 100 classes foram selecionadas, abrangendo os principais produtos. Cada classe foi alimentada com milhares de exemplos para que fosse possível ao modelo abstrair as principais características de cada produto. Após treinamento do modelo utilizando redes neurais convolucionais, o modelo obteve uma acurácia média de 88,21%, alcançando o melhor resultado de 89,77%.Referências
Franco, A., Maltoni, D., and Papi, S. (2017). Grocery product detection and recognition. Expert Systems with Applications, 81:163 – 176.
Guimarães, V., Nascimento, J., Viana, P., and Carvalho, P. (2023). A review of recent advances and challenges in grocery label detection and recognition. Applied Sciences,13(5).
Koubaroulis, D., Mata, J., and Kittl, J. (2002). Evaluating Colour-Based Object Recognition Algorithms Using the SOIL-47 Database. In 5th Asian Conference on Computer Vision, Australia.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521:436–444.
Melek, C. G., Battini Sonmez, E., and Varlı, S. (2024). Datasets and methods of product recognition on grocery shelf images using computer vision and machine learning approaches: An exhaustive literature review. Engineering Applications of Artificial Intelligence, 133:108452.
Merler, M., Galleguillos, C., and Belongie, S. (2007). Recognizing groceries in situ using in vitro training data. In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8.
Pietrini, R., Paolanti, M., Mancini, A., Frontoni, E., and Zingaretti, P. (2024). Shelf management: A deep learning-based system for shelf visual monitoring. Expert Systems with Applications, 255:124635.
Selvam, P., Faheem, M., Dakshinamurthi, V., Nevgi, A., Bhuvaneswari, R., Deepak, K., and Abraham Sundar, J. (2024). Batch normalization free rigorous feature flow neural network for grocery product recognition. IEEE Access, 12:68364–68381.
Szeliski, R. (2010). Computer Vision: Algorithms and Applications.
Tonioni, A., Serra, E., and di Stefano, L. (2018). A deep learning pipeline for product recognition on store shelves. 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS), pages 25–31.
Yadav, S. and Shukla, S. (2016). Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. 2016 IEEE 6th International Conference on Advanced Computing (IACC), pages 78–83.
Guimarães, V., Nascimento, J., Viana, P., and Carvalho, P. (2023). A review of recent advances and challenges in grocery label detection and recognition. Applied Sciences,13(5).
Koubaroulis, D., Mata, J., and Kittl, J. (2002). Evaluating Colour-Based Object Recognition Algorithms Using the SOIL-47 Database. In 5th Asian Conference on Computer Vision, Australia.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521:436–444.
Melek, C. G., Battini Sonmez, E., and Varlı, S. (2024). Datasets and methods of product recognition on grocery shelf images using computer vision and machine learning approaches: An exhaustive literature review. Engineering Applications of Artificial Intelligence, 133:108452.
Merler, M., Galleguillos, C., and Belongie, S. (2007). Recognizing groceries in situ using in vitro training data. In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8.
Pietrini, R., Paolanti, M., Mancini, A., Frontoni, E., and Zingaretti, P. (2024). Shelf management: A deep learning-based system for shelf visual monitoring. Expert Systems with Applications, 255:124635.
Selvam, P., Faheem, M., Dakshinamurthi, V., Nevgi, A., Bhuvaneswari, R., Deepak, K., and Abraham Sundar, J. (2024). Batch normalization free rigorous feature flow neural network for grocery product recognition. IEEE Access, 12:68364–68381.
Szeliski, R. (2010). Computer Vision: Algorithms and Applications.
Tonioni, A., Serra, E., and di Stefano, L. (2018). A deep learning pipeline for product recognition on store shelves. 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS), pages 25–31.
Yadav, S. and Shukla, S. (2016). Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. 2016 IEEE 6th International Conference on Advanced Computing (IACC), pages 78–83.
Publicado
24/04/2025
Como Citar
FIGUEIREDO, Vinícius D. A.; VENTURA, Thiago M.; GOMES, Raphael de S. R.; VITORIANO, Fabio S..
Uso de deep learning na classificação de imagens de produtos de um pet shop. In: ESCOLA REGIONAL DE SISTEMAS DE INFORMAÇÃO DE MATO GROSSO, 1. , 2025, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 21-27.
DOI: https://doi.org/10.5753/ersimt.2025.8047.
