Supervised computer vision system for weight group classification of fingerlings

  • Adair da S. O. Junior UFMS
  • Ana Karina V. da Silva UCDB
  • Marcio C. B. Pache IFMS
  • Diego A. Sant’Ana IFMS
  • Alexsandro M. Carneiro
  • Pedro L. F. Albuquerque UCDB
  • Vanir Garcia IFMS
  • Fabricio de L. Weber University of Nebraska–incoln
  • Vanessa A. Weber University of Nebraska–incoln
  • Hemerson Pistori UCDB

Resumo


Classifying weight ranges is essential in fish farms since they are sold according to the fingerlings’ minimum size, uniformity, and maximum size. Therefore, evaluating the batches’ quality is fundamental, which analyzes the growth rate, feed conversion, and survival rate, among others. This paper aims to classify weight ranges for fingerlings of Pintado Real using supervised learning techniques. For this purpose, 60 images were captured, containing a 10-cent Real coin and a ruler next to each fingerling. The software was designed to extract attributes from the images and then serve as inputs for Weka’s training algorithms. The J48 algorithm obtained a performance 76.66% in the accuracy metric, and the ANOVA shows no statistical difference. This result is promising since the dataset of images taken from varying distances is a situation that is often common in this type of collection, and the proposed software takes care of standardizing the scale.

Palavras-chave: weight range classification, image processing, smart fish farm, Pseudoplatystoma corruscans

Referências

M. Henchion, M. Hayes, A. Mullen, M. Fenelon, and T. Brijesh kumar, “Future protein supply and demand: Strategies and factors influencing a sustainable equilibrium,” Foods, vol. 6, p. 53, 07 2017.

FAO, “A quarterly update on world seafood markets april 2019 issue, with january–december 2018 statistics,” 2019.

——, “Chapter 8. fish and seafood,” 2018.

——, “Aquaculture technology,” 2020.

P. L. FRANÇA ALBUQUERQUE, V. Garcia, A. da Silva Oliveira, T. Lewandowski, C. Detweiler, A. B. Gonçalves, C. S. Costa, M. H. Naka, and H. Pistori, “Automatic live fingerlings counting using computer vision,” Computers and Electronics in Agriculture, vol. 167, p. 105015, 2019. [Online]. Available: [link]

G. Kumar, C. Engle, and C. Tucker, “Factors driving aquaculture technology adoption,” Journal of the World Aquaculture Society, vol. 49, 03 2018.

F. Suplicy, “National Aquaculture Sector Overview. Brazil. National Aquaculture Sector Overview Fact Sheets.” 2004. [Online]. Available: [link]

F. Kubitza, “Brazilian aquaculture: Constraints and challenges (Part 1),” p. 7, 2016. [Online]. Available: [link].

V. Garcia, D. Sant’Ana, V. Zanoni, M. Pache, M. Naka, P. Albuquerque, T. Lewandowski, A. Junior, J. Rozales, M. Ferreira, E. Queiroz, J. Almanza, and H. Pistori, “A new image dataset for the evaluation of automatic fingerlings counting,” Aquacultural Engineering, p. 102064, 02 2020.

F. Mustafa, “A review of smart fish farming systems,” Journal of Aquaculture Engineering and Fisheries Research, pp. 193–200, 01 2016.

X. Yang, S. Zhang, J. Liu, Q. Gao, S. Dong, and C. Zhou, “Deep learning for smart fish farming: applications, opportunities and challenges,” Reviews in Aquaculture, vol. 13, no. 1, pp. 66–90, 2021. [Online]. Available: [link].

A. Ramya, R. Rohini, and S. Ravi, “Iot based smart monitoring system for fish farming,” International Journal of Engineering and Advanced Technology, vol. 8, no. 6 Special Issue, pp. 420–424, Aug. 2019.

T. Y. Kyaw and A. K. Ng, “Smart aquaponics system for urban farming,” Energy Procedia, vol. 143, pp. 342–347, 2017, leveraging Energy Technologies and Policy Options for Low Carbon Cities. [Online]. Available: [link].

Y.-H. Hsiao, C.-C. Chen, S.-I. Lin, and F.-P. Lin, “Real-world underwater fish recognition and identification, using sparse representation,” Ecological Informatics, vol. 23, pp. 13–21, 2014, special Issue on Multimedia in Ecology and Environment. [Online]. Available: [link].

P. X. Huang, B. J. Boom, and R. B. Fisher, “Hierarchical classification with reject option for live fish recognition,” Machine Vision and Applications, vol. 26, no. 1, pp. 89–102, Jan 2015. [Online]. Available: https://doi.org/10.1007/s00138-014-0641-2

S. Palazzo and F. Murabito, “Fish species identification in real-life underwater images,” in Proceedings of the 3rd ACM International Workshop on Multimedia Analysis for Ecological Data, ser. MAED ’14. New York, NY, USA: Association for Computing Machinery, 2014, p. 13–18. [Online]. Available: https://doi.org/10.1145/2661821.2661822

S. Z. Shah, H. T. Rauf, M. I. Lali, M. Khalid, M. Farooq, M. Fatima, and S. A. C. Bukhari, “Fish-pak: Fish species dataset from pakistan for visual features based classification,” Data in Brief, vol. 27, p. 104565, 10 2019.

A. Santos and W. Gonçalves, “Improving pantanal fish species recognition through taxonomic ranks in convolutional neural networks,” Ecological Informatics, vol. 53, p. 100977, 06 2019.

M. Mathur, D. Vasudev, S. Sahoo, D. Jain, and N. Goel, “Crosspooled fishnet: transfer learning based fish species classification model,” Multimedia Tools and Applications, vol. 79, no. 41, pp. 31 625–31 643, Nov 2020. [Online]. Available: https://doi.org/10.1007/s11042-020-09371-x

U. Freitas, W. N. Gonçalves, E. T. Matsubara, J. Sabino, M. R. Borth, and H. Pistori, “Using color for fish species classification,” in Electronic Proceedings of the 29th Conference on Graphics, Patterns and Images (SIBGRAPI’16), F. A. M. Cappabianco, F. A. Faria, J. Almeida, and T. S. Körting, Eds., São José dos Campos, SP, Brazil, october 2016. [Online]. Available: [link]

A. Jalal, A. Salman, A. Mian, M. Shortis, and F. Shafait, “Fish detection and species classification in underwater environments using deep learning with temporal information,” Ecological Informatics, vol. 57, p. 101088, 2020. [Online]. Available: [link].

A. Banan, A. Nasiri, and A. Taheri-Garavand, “Deep learning-based appearance features extraction for automated carp species identification,” Aquacultural Engineering, vol. 89, p. 102053, 05 2020.

A. Taheri-Garavand, A. Nasiri, A. Banan, and Y.-D. Zhang, “Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish,” Journal of Food Engineering, vol. 278, p. 109930, 08 2020.

A. da Silva Oliveira Junior, V. Garcia, H. Pistori, V. A. de Moraes Weber, D. A. Sant’Ana, M. C. B. Pache, A. K. V. da Silva, A. M. Carneiro, and P. L. F. Albuquerque, “Alev60p,” 2023. [Online]. Available: [link]

R. Kohavi, “A study of cross-validation and bootstrap for accuracy estimation and model selection,” in Appears in the International Joint Conference on Arti cial Intelligence (IJCAI), vol. 14, 03 2001.

D. Aha and D. Kibler, “Instance-based learning algorithms,” Machine Learning, vol. 6, pp. 37–66, 1991.

R. Quinlan, C4.5: Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann Publishers, 1993.

J. Platt, “Fast training of support vector machines using sequential minimal optimization,” in Advances in Kernel Methods - Support Vector Learning, B. Schoelkopf, C. Burges, and A. Smola, Eds. MIT Press, 1998. [Online]. Available: [link]

S. Keerthi, S. Shevade, C. Bhattacharyya, and K. Murthy, “Improvements to platt’s smo algorithm for svm classifier design,” Neural Computation, vol. 13, no. 3, pp. 637–649, 2001.

T. Hastie and R. Tibshirani, “Classification by pairwise coupling,” in Advances in Neural Information Processing Systems, M. I. Jordan, M. J. Kearns, and S. A. Solla, Eds., vol. 10. MIT Press, 1998.
Publicado
13/11/2023
O. JUNIOR, Adair da S. et al. Supervised computer vision system for weight group classification of fingerlings. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 18. , 2023, São Bernardo do Campo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 142-147. DOI: https://doi.org/10.5753/wvc.2023.27547.