Counting granules with u-net networks and connected components

Authors

DOI:

https://doi.org/10.26439/ing.ind2022.n.5804

Keywords:

artificial intelligence, computer vision, neural networks, automation

Abstract

This research develops a methodology to automate the process of counting the number of granules that remains in a toilet after being flushed (ASME A112.19.2-2018/CSA B45.1-18). This work integrates a U-Net convolutional network with a variation of the connected component algorithm. The training set consisted of 3678 images. Results show an accuracy above 98% between 0 and 180 granules. The methodology has been implemented in the production line.

Downloads

Download data is not yet available.

Author Biographies

  • Juan Felipe Monsalvo Salazar, Organización Corona, Medellín, Colombia

    Magíster en Mecánica Computacional por la Universidad EAFIT de Medellín, Colombia, y magíster en Diseño Mecánico por la École Nationale d’Ingénieurs de Tarbes, Francia. Ingeniero mecánico por la Universidad EAFIT. Actualmente, se desempeña como ingeniero de desarrollo de producto en la Organización Corona, empresa colombiana con 140 años de trayectoria en la industria de cerámica, y apoya los procesos de transformación digital, machine learning y business analytics en la organización. Sus áreas de trabajo incluyen desarrollos en visión artificial, detección de objetos, predicción de la demanda y optimización de la cadena de suministro.

  • Juan Rodrigo Jaramillo Posada, Adelphi University, Facultad de Negocios, Nueva York, Estados Unidos

    Doctor en Ingeniería Industrial por la Universidad de Virginia Occidental, Estados Unidos. Director de la maestría en Analítica en la Facultad de Negocios de la Universidad de Adelphi en Nueva York, Estados Unidos. Codirector del prestigioso Innovative Applications in Analytics Award. Sus publicaciones incluyen las áreas de logística, optimización y analítica aplicada, y es invitado con frecuencia a participar en paneles y conferencias sobre analítica e inteligencia artificial.

References

Alam, M., & Islam, M. (2019). Machine learning approach of automatic identification and counting of blood cells. Healthcare Technology Letters, 6(4), 103-108. DOI: 10.1049/htl.2018.5098

Bradski, G. (2000). The OpenCV Library. Journal of Software Tools, 25, 120-125.

Dobrescu, A., Giuffrida, M., & Tsaftaris A. (2019). Understanding deep neural networks for regression in leaf counting. En IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 2600-2608). DOI: 10.1109/CVPRW.2019.00316

Fukushima, K. (1980). Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, 36(4), 193-202. https://doi.org/10.1007/BF00344251

Hough, P. (1962). Method and means for recognizing complex patterns (US Patent 3, 069,654, Ser. N.o 17,7156 Claims).

Ilyas, N., Shahzad, A., & Kim, K. (2020). Convolutional-neural network-based image crowd counting: review, categorization, analysis, and performance evaluation. Sensors, 20(1). https://doi.org/10.3390/s20010043

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: convolutional networks for biomedical image segmentation. https://arxiv.org/abs/1505.04597

Shamsaldin, A., Fattahb, P., Rashid, T., & Al-Salihi, N. (2019). A study of the convolutional neural networks applications. UKH Journal of Science and Engineering, 3(2), 31-40. https://doi.org/10.25079/ukhjse.v3n2y2019.pp31-40

Wu, J., Yang, G., Yang, X., Xu, B., Han, L., & Zhu, Y. (2019). Automatic counting of in situ rice seedlings from UAV images based on a deep fully convolutional neural network. Remote Sensing, 11(6), 691. https://doi.org/10.3390/rs11060691

Yong, H., Hong, Z., Yangyang, F., Shuaisheng, J., & Jianjian, W. (2019). Application of deep learning in integrated pest management: a real-time system for detection and diagnosis of oilseed rape pests. Mobile Information Systems, 2019, Artículo 4570808. https://doi.org/10.1155/2019/4570808

Zhao, M., Zhang, J., Zhang, C., & Zhang, W. (2018). Towards locally consistent object counting with constrained multi-stage convolutional neural networks. En Asian Conference on Computer Vision (pp. 247-261). Springer. https://doi.org/10.1007/978-3-030-20876-9_16

Downloads

Published

2022-04-22

Issue

2022: Edición Especial

Section

Artículos

How to Cite

Counting granules with u-net networks and connected components. (2022). Ingeniería Industrial, 137-153. https://doi.org/10.26439/ing.ind2022.n.5804