Sistema automático de clasificación de peces

Automatic fish classification system

  • Robinson Jiménez Moreno
  • Javier Eduardo Martínez Baquero
  • Luis Alfredo Rodríguez Umaña
Palabras clave: machine learning, deep learning, pattern recognition, fish classification, machine vision, CNN (en_US)
Palabras clave: aprendizaje de máquina, aprendizaje profundo, reconocimiento de patrones, clasificación de peces, visión de máquina, RNC (es_ES)

Resumen (es_ES)

el presente artículo expone el diseño de una arquitectura de red para reconocimiento de patrones orientada a la clasificación automática de dos tipos de peces: mojarra y tilapia. Se emplea una arquitectura basada en aprendizaje profundo mediante una red neuronal convolucional (RNC) para la cual se determina la base de datos a emplear y los diferentes hiperparámetros que la componen. Se logra obtener, mediante análisis por matriz de confusión, un desempeño del 100% de la red bajo las condiciones controladas el sistema de clasificación, es decir: color de banda transportadora uniforme y uso de luz día.

Resumen (en_US)

the present article exposes the design of a network architecture for pattern recognition, oriented to the automatic classification of two types of fish: mojarra and tilapia. An architecture based on deep learning is used by means of a convolutional neuronal network (CNN), for which the database to be used and the different hyperparameters that compose it are determined. It is possible to obtain, through confusion matrix analysis, a 100% performance of the network under the controlled conditions of the classification system, that is: uniform conveyor belt color and daylight use.

Descargas

La descarga de datos todavía no está disponible.

Referencias

O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg y L. Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge”

International Journal of Computer Vision (IJCV), vol. 115, n° 3, pp. 211–252, 2015, https://doi.org/10.1007/s11263-015-0816-y

J. Deng, W. Dong, R. Socher, L. Li, K. Li y L. FeiFei, “Imagenet: A large-scale hierarchical image database” In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248–255. IEEE, 2009.

ImageNet, “Imagenet large scale visual recognition challenge 2012 (ilsvrc2012)” [En línea], Disponible en: http://www.image-net.org/challenges/LSVRC/2012/

P. Y. Simard, D. Steinkraus, J.C. Platt, et al, “Best practices for convolutional neural networks applied to visual document analysis” In ICDAR, vol. 3, pp. 958–962, 2003, https://doi.org/10.1109/ICDAR.2003.1227801

F. Nasse, C. Thurau y G.A. Fink, “Face detection using GPU-based convolutional neural networks” In International Conference on Computer Analysis of Images and Patterns, pp. 83–90. Springer, 2009, https://doi.org/10.1007/978-3-642-03767-2_10

Y. Taigman, M. Yang, M. Ranzato y L. Wolf, “Deepface: Closing the gap to human-level performance in face verification” In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1701–1708, 2014, https://doi.org/10.1109/CVPR.2014.220

S. Ren, K. He, R. Girshick y J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks” In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems 28, pp. 91–99. Curran Associates, Inc., 2015.

T. Guo, J. Dong, H. Li y Y. Gao, "Simple convolutional neural network on image classification," 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(, Beijing, 2017, pp. 721-724, https://doi.org/10.1109/ICBDA.2017.8078730

A. Giyenko, A. Palvanov y Y. Cho, "Application of convolutional neural networks for visibility estimation of CCTV images," 2018 International Conference on Information Networking (ICOIN), Chiang Mai, 2018, pp. 875-879, https://doi.org/10.1109/ICOIN.2018.8343247

B. Zhu et al., "Learning Environmental Sounds with Multi-scale Convolutional Neural Network," 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, 2018, pp. 1-8, https://doi.org/10.1109/IJCNN.2018.8489641

Jia-Hong Lee, Mei-Yi Wu y Zhi-Cheng Guo, "A tank fish recognition and tracking system using computer vision techniques," 2010 3rd International Conference on Computer Science and Information Technology, Chengdu, 2010, pp. 528-532, https://doi.org/10.1109/ICCSIT.2010.5563625

X. Zheng, J. Zhong y Y. Zhang, "A SOA-Based Fish Recognition System Prototype," 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics, Zhejiang, 2011, pp. 66-69,

https://doi.org/10.1109/IHMSC.2011.86

Y. Nishida, T. Ura, T. Hamatsu, K. Nagahashi, S. Inaba and T. Nakatani, "Fish recognition method using vector quantization histogram for investigation of fishery resources," 2014 Oceans - St. John's, St. John's, NL, 2014, pp. 1-5, https://doi.org/10.1109/OCEANS.2014.7003268

Y. Wang, H. Ye y B. Li, "A research based on recognition algorithm of characteristics of body surface of infected fish," 2010 World Automation Congress, Kobe, 2010, pp. 155-160.

L. Shi, R. Guo and Y. Ma, "A novel artificial fish swarm algorithm for pattern recognition with convex optimization," 2016 International Conference on Communication and Electronics Systems (ICCES), Coimbatore, 2016, pp. 1-4, https://doi.org/10.1109/CESYS.2016.7889830

S. Luo, X. Li, D. Wang, J. Li and C. Sun, "Automatic Fish Recognition and Counting in Video Footage of Fishery Operations," 2015 International Conference on Computational Intelligence and Communication Networks (CICN), Jabalpur, 2015, pp. 296-299, https://doi.org/10.1109/CICN.2015.66

G. Ding et al., "Fish recognition using convolutional neural network," OCEANS 2017 - Anchorage, Anchorage, AK, 2017, pp. 1-4.

A. Krizhevsky; I. Sutskever; G. Hinton. Imagenet classification with deep convolutional neural networks. En Advances in neural information processing systems. 2012. pp. 1097-1105.

M. D. Zeiler, y R. Fergus, “Visualizing and Understanding Convolutional Networks”. ECCV 2014, Part I, LNCS 8689, pp. 818–833, 2014. Springer International Publishing Switzerland 2014, https://doi.org/10.1007/978-3-319-10590-1_53

M.Aursand, I.B. Standal, A. Praël, L. McEvoy, J. Irvine y D.E. Axelson, “13C NMR pattern recognition techniques for the classification of atlantic salmon (salmo salar l.) according to their wild, farmed, and geographical origin”, Journal of agricultural and food chemistry, vol. 57, n° 9, pp. 3444–3451, 2009, https://doi.org/10.1021/jf8039268

M.A. Nanny, R.A. Minear y J.A. Leenheer, “Nuclear magnetic resonance spectroscopy in environmental chemistry”, Oxford University Press, 1997.

X. Li, M. Shang, H. Qin y L. Chen “Fast accurate fish detection and recognition of underwater images with fast r-cnn”. In OCEANS’15 MTS/IEEE Washington, pp. 1–5. IEEE, 2015.

H. Qin, X. Li, J. Liang, Y. Peng y C. Zhang, “Deepfish: Accurate underwater live fish recognition with a deep architecture” Neurocomputing, vol. 187, pp. 49–58, 2016, https://doi.org/10.1016/j.neucom.2015.10.122

L. Jin y H. Liang, “Deep learning for underwater image recognition in small sample size situations” In OCEANS 2017-Aberdeen, pp. 1–4. IEEE, 2017, https://doi.org/10.1109/OCEANSE.2017.8084645

P.X. Huang, B.B. Boom y R.B. Fisher “Fish recognition ground-truth data” [En línea], Disponible en: http://groups.inf.ed.ac.uk/f4k/GROUNDTRUTH/RECOG/

Cómo citar
Jiménez Moreno, R., Martínez Baquero, J., & Rodríguez Umaña, L. (2018). Sistema automático de clasificación de peces. Visión Electrónica, 12(2). https://doi.org/10.14483/22484728.14265
Publicado: 2018-12-12
Sección
Visión de Caso