Pig Weight Estimation Using Image Processing and Artificial Neural Networks
Article Sidebar
Main Article Content
Abstract
The purpose of this study was to determine a method for estimating pig weight using image processing and neural networks. Weight, head circumference, body length and top view of a hundred pigs, the sample groups, were recorded once at a time. Python was applied for analyzing the top view of each pig to find the pig’s pixel-to-total. The data were classified into two groups, the practice set (n=70) and the test set (n=30). The relationship between body weight regarding circumference and length regarding body image, was determined by the Pearson Product Moment Correlation (PPMC). The aim is at developing pig weight equations where K-Nearest Neighbors (K-NN), Artificial Neural Networks (ANN), Mean Absolute Deviation (MAD), and Mean Absolute Percentage Error (MAPE) were measurement errors of the estimation. The results were about 86% accuracy. It can be concluded that the image processing was a quick method for estimating body weight without stressing the pigs. Artificial neural network is an alternative method to improve the accuracy of pig weight estimation.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The author has the sole responsibility for the material published in RTNA Journal of Science and Technology, which the editorial board may not agree on that material.
RTNA Journal of Science and Technology owns the copyright of the text, the illustration, or other material published in the journal. No parts or the whole of the material published may be disseminated or used in any form without first obtaining written permission from the academy.
References
Brandl N, Jorgensen E. Determination of live weight of pigs from dimensions measured using image analysis. Comput Electron Agric [Internet]. 1996 May [cited 2022 Mar 10]; 15(1):57-72. Available from: https://www.sciencedirect.com/science/article/abs/pii/0168169996000038
Sungirai M, Masaka L, Benhura TM. Validity of weight estimation models in pigs reared under different management conditions. Vet Med Int [Internet]. 2014 May [cited 2022 Mar 25];2014:[about 10 p.]. Available from: https://www.hindawi.com/journals/vmi/2014/530469/.
Kashiha M, Bahr C, Ott S, Moons CPH, Niewold TA, Ödberg FO, Berckmans D. Automatic weight estimation of individual pigs using image analysis. Comput Electron Agric [Internet]. 2014 Sep [cited 2022 Mar 7];107:38-44. Available from: https://www.sciencedirect.com/science/article/ abs/pii/S0168169914001525
Jun K, Kim SJ, Ji HW. Estimating pig weights from images without constraint on posture and illumination. Comput Electron Agric [Internet]. 2018 Oct [cited 2022 Mar 15];153:169-76. Available from: https://www.researchgate.net/publication/327993584_Estimating_pig_ weights_from_images_without_constraint_on_posture_and_illumination
Win KD, Kawasue K, Yoshida K, Lee G. Automatic pig selection system based on body size using a camera: rotating mechanics for pig selection. Artif Life Robot [Internet]. 2021 [cited 2022 Mar 22];2021(2):155–61. Available from: https://www.springerprofessional.de/en/artificial-life-and-robotics-2-2021/19088304
Kaewtapee C, Rakangtong C, Bunchasak C. Pig Weight Estimation Using Image Processing and Artificial Neural Networks. Journal of Advanced Agricultural Technologies [Internet]. 2019 Dec [cited 2022 Mar 23];6(4):253-56. Available from: http://www.joaat.com/index.php?m=content&c =index&a=show&catid=57&id=348
C. Kaewtapee, Khetchaturat C, Bunchasak C. Comparison of growth models between artificial neural networks and nonlinear regression analysis in Cherry Valley ducks. J Appl Poult Res [Internet]. 2011 Dec [cited 2022 Mar 25];20(4):421-28. Available from: https://www.researchgate.net/publication/270080550_Comparison_of_growth_models_
between_artificial_neural_networks_and_nonlinear_regression_analysis_in_Cherry_Valley_ducks
Roush WB, Dozier III WA, Branton SL. Comparison of Gompertz and neural network models of broiler growth. Poult Sci [Internet]. 2006 May [cited 2022 Mar 25];85(4):794-97. Available from: https://www.researchgate.net/publication/7165614_Comparison_of_Gompertz_
and_nEural_Network_Models_of_Broiler_Growth
Kaewtapee C, Khetchaturat C, Bunchasak C. Prediction of standardized ileal lysine digestibility in heated full-fat soybeans by artificial neural networks. Present at the 18th AAAP Congress; 2018 Aug 1-5. Malaysia. Kuching: [publisher unknown]; 2018.
Ahmad HA, Dozier GV, Roland DA. Egg price forecasting using neural networks. J Appl Poult Res [Internet]. 2001 Jun [cited 2022 Mar 25];10(2):162-71. Available from: https://www.researchgate.net/publication/251811793_Egg_Price_Forecasting_Using_Neural_Networks
Kaewtapee C, Khetchaturat C, Krutthai N, Bunchasak C. Soybean meal price forecasting using artificial neural network. Journal of Agricultural Research and Extension [Internet]. 2018 Aug [cited 2022 Mar 26];352(2):392-99. Available from: https://www.cabdirect.org/cabdirect/ abstract/20193172456
Wang Y, Yang W, Winter P, Walker L. Walk-through weighing of pigs using machine vision and an artificial neural network. Biosystem Engineering [Internet]. 2008 May [cited 2022 Mar 26];100(1):117-25. Available from: https://www.researchgate.net/publication/229393183_Walk-through_weighing_of_pigs_using_machine_vision_and_an_artificial_neural_network
Gonzales R, Woods RE. Digital Image Processing, 2nd ed. Upper-Saddle River, NJ: Prentice Hall; 2002.
