Context-based segmentation of the longissimus muscle in beef with a deep neural network

Main Article Content

Karol Talacha
Izabella Antoniuk
Leszek Chmielewski
Michał Kruk
Jarosław Kurek
Arkadiusz Orłowski
Jakub Pach
Andrzej Półtorak
Bartosz Świderski
Grzegorz Wieczorek


Keywords : beef carcasses, context-based, segmentation, longissimus muscle, classification, deep convolutional network, beef quality
Abstract

The problem of segmenting the cross-section through the longissimus muscle in beef carcasses with computer vision methods was investigated. The available data were 111 images of cross-sections coming from 28 cows (typically four images per cow). Training data were the pixels of the muscles, marked manually. The AlexNet deep convolutional neural network was used as the classifier, and single pixels were the classified objects. Each pixel was presented to the network together with its small circular neighbourhood, and with its context represented by the further neighbourhood, darkened by halving the image intensity. The average classification accuracy was 96%. The accuracy without darkening the context was found to be smaller, with a small but statistically significant difference. The segmentation of the longissimus muscle is the introductory stage for the next steps of assessing the quality of beef for the alimentary purposes.

Article Details

How to Cite
Talacha, K., Antoniuk, I., Chmielewski, L., Kruk, M., Kurek, J., Orłowski, A., Pach, J., Półtorak, A., Świderski, B., & Wieczorek, G. (2019). Context-based segmentation of the longissimus muscle in beef with a deep neural network. Machine Graphics and Vision, 28(1/4), 47–57. https://doi.org/10.22630/MGV.2019.28.1.5
References

S. Agustin and R. Dijaya. Beef image classification using k-nearest neighbor algorithm for identification quality and freshness. Journal of Physics: Conference Series, 1179:012184, July 2019. https://doi.org/10.1088/1742-6596/1179/1/012184. (Crossref)

M. Al-Sarayreh, M. M. Reis, W. Q. Yan, and R. Klette. Detection of red-meat adulteration by deep spectral-spatial features in hyperspectral images. Journal of Imaging, 4(5), 2018. https://doi.org/10.3390/jimaging4050063. (Crossref)

A. E. Andaya, E. R. Arboleda, A. A. Andilab, and R. M. Dellosa. Meat marbling scoring using image processing with fuzzy logic based classifier. Int. J. of Scientific & Technology Research, 8(8):1442–1445, Feb. 2018. http://www.ijstr.org/research-paper-publishing.php?month=aug2019.

D. F. Barbin, S. M. Mastelini, S. Barbon, G. F. C. Campos, A. P. A. C. Barbon, and M. Shimokomaki. Digital image analyses as an alternative tool for chicken quality assessment. Biosystems Engineering, 144:85–93, 2016. https://doi.org/10.1016/j.biosystemseng.2016.01.015. (Crossref)

C.-J. Du, A. Iqbal, and D.-W. Sun. Quality measurement of cooked meats. In D.-W. Sun, editor, Computer Vision Technology for Food Quality Evaluation (Second Edition), chapter 8, pages 195–212. Academic Press, San Diego, second edition, 2016. https://doi.org/10.1016/B978-0-12-802232-0.00008-6. (Crossref)

R. J. S. De Guzman, D. N. N. Niro, and A. C. F. Bueno. Pork quality assessment through image segmentation and support vector machine implementation. Journal of Technology Management and Business, 5(2), Feb. 2018. https://publisher.uthm.edu.my/ojs/index.php/jtmb/article/view/2261. (Crossref)

P. Jackman, D.-W. Sun, and P. Allen. Automatic segmentation of beef longissimus dorsi muscle and marbling by an adaptable algorithm. Meat Science, 83(2):187–194, 2009. https://doi.org/10.1016/j.meatsci.2009.03.010. (Crossref)

M. Kamruzzaman, Y. Makino, and S. Oshita. Online monitoring of red meat color using hyperspectral imaging. Meat Science, 116:110–117, 2016. https://doi.org/10.1016/j.meatsci.2016.02.004. (Crossref)

A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. Commun. ACM, 60(6):84–90, May 2017. https://doi.org/10.1145/3065386. (Crossref)

I. Muñoz, P. Gou, and E. Fulladosa. Computer image analysis for intramuscular fat segmentation in dry-cured ham slices using convolutional neural networks. Food Control, 106:106693, 2019. https://doi.org/doi.org/10.1016/j.foodcont.2019.06.019. (Crossref)

X. Sun, J. Young, J. H. Liu, L Bachmeier, R. M. Somers, K. J. Chen, and D. Newman. Prediction of pork color attributes using computer vision system. Meat Science, 113:62–64, 2016. https://doi.org/10.1016/j.meatsci.2015.11.009. (Crossref)

A. Taheri-Garavand, S. Fatahi, M. Omid, and Y. Makino. Meat quality evaluation based on computer vision technique: A review. Meat Science, 156:183–195, 2019. https://doi.org/10.1016/j.meatsci.2019.06.002. (Crossref)

J. Tan. Meat quality evaluation by computer vision. Journal of Food Engineering, 61(1):27–35, 2004. https://doi.org/10.1016/S0260-8774(03)00185-7. (Crossref)

Statistics

Downloads

Download data is not yet available.
Recommend Articles
Most read articles by the same author(s)
1 2 > >>