Abstract

As to the problem of inaccurate in traditional grade method of beef marbling, a automatic grading system based on computer vision had been founded and was used to predict the beef quality grade of Chinese yellow cattle. Image processing was used to automatically evaluate the beef marbling grade. Segmentation methods used in rib-eye image of beef carcass was improved watershed algorithm. All grading indicators were obtained by image processing automatically. Four grading indicators, which characterize the size, number and distribution of marbling particles, were proposed for the inputs of neural network prediction model. The experimental results indicated that the image processing methods were effective. The grading system based on computer vision and neural network model can better predict the beef quality grading. The prediction accuracy of beef marbling grade was 86.84%. Algorithm proposed in this study proved the image processing and neural network modeling is an effective method for beef marbling grading.

Keywords:

Beef marbling grade, improved watershed, machine vision, neural network,

References

1. Ballerini, L., A. Högberg, K. Lundström and G. Borgefors, 2001. Color image analysis technique for measuring of fat in meat: An Application for the Meat Industry. In: Hunt, M.A. (Ed.), Proceedings of SPIE Volume: 4301, Machine Vision Applications in Industrial Inspection IX, April 2001, San Jose', California, USA.
   
2. Chen, K. and C. Qin, 2008. Segmentation of beef marbling based on vision threshold. Comput. Electron. Agr., 62(2): 223-230.
   CrossRef    
3. Chen, K., X. Sun and C. Qin, 2010. Color grading of beef fat by using computer vision and support vector machine. Comput. Electron. Agr., 70(1): 27-32.
   CrossRef    
4. Du, C.J. and D.W. Sun, 2004. Recent developments in the applications of image processing techniques for food quality evaluation. Trends Food Sci. Technol., 15(5): 230-249.
   CrossRef    
5. Du, C.J., D.W. Sun, P. Jackman and P. Allen, 2008. Development of a hybrid image processing algorithm for automatic evaluation of intramuscular fat content in beef M. longissimus dorsi. Meat Sci., 80(4): 1231-1237.
   CrossRef    PMid:22063863    
6. Fumito, Y., T. Kazuo, W. Koichi and N. Ostu, 2000. On a grading system for beef marbling. Pattern Recogn. Lett., 21(12): 1037-1050.
   CrossRef    
7. Gao, X., J. Tan and D.E. Gerrard, 1995. Image segmentation in 3-dimensional color space. ASAE Annual International Meeting, Paper No. 953607, ASAE, St. Joseph, MI, USA.
   
8. Gerrard, D.E., X. Gao and J. Tan, 1996. Beef marbling and color score determination by image processing. J. Food Sci., 61(1): 145-148.
   CrossRef    
9. Huan, L.N., S. Choi, S.I. Cho, M.H. Lee and H. Heon, 2009. Automatic extraction of lean-tissue contours for beef quality grading. Biosyst. Eng., 102(3): 251-264.
   CrossRef    
10. Jackman, P., D.W. Sun, C.J. Du, P. Allen and G. Downey, 2008. Prediction of beef eating quality from color, marbling and wavelet texture features. Meat Sci., 80(4): 1273-1281.
    CrossRef    PMid:22063868    
11. Jeyamkondan, S., N. Ray and G.A. Kranzler, 2000. Beef quality grading using machine vision. Proceedings of the Conference on Biological Quality and Precision Agriculture II. Boston, USA, pp: 91-101.
    CrossRef    
12. Jinglu, T., 2004. Meat quality evaluation by computer vision. J. Food Eng., 72(1): 39-55.
    
13. Kazuhiko, S., H. Kenichiro and O. Akifumi, 2000a. Grading meat quality by image processing. Pattern Recogn., 33(6): 97-104.
    
14. Kazuhiko, S., H. Kenichiro and O. Akifumi, 2000b. Determination of meat quality by image processing and neural network techniques. Proceeding of the 9th IEEE International Conference on Fuzzy Systems, 2: 989-992.
    
15. Kazuo, T., W.H.K. Paul, K. Kazuki, S. Tetsuo and W. Koichi, 2002. On a fluency image coding system for beef marbling evaluation. Pattern Recogn. Lett., 23(11): 1277-1291.
    CrossRef    
16. Kuchida, K., K. Yamaki and Y. Mizuma, 1992. Evaluation of meat quality in Japanese beef cattle by computer image analysis. Anim. Sci. Technol., 63(2): 121-128.
    CrossRef    
17. Lee, S.U., S.Y. Chung and R.H. Park, 1990. A comparative performance study of several global thresholding techniques for segmentation. Lect. Notes Comput. Sc., 52(2): 171-190.
    CrossRef    
18. Li, Y., J. Shan and Y. Peng, 2011. Nondestructive assessment of beef-marbling grade using hyperspectral imaging technology. Proceedings of International Conference on New Technology of Agricultural Engineering, pp: 779-783.
    
19. Liu, M., J. Zhao and H. Zhang, 2004. Segmentation of fat and lean meat in beef images based on fuzzy C-means clustering. T. Chinese Soc. Agric. Eng., 20(2): 161-163, (In Chinese).
    
20. McDonald, T. and Y.R. Chen, 1990. Separating connected muscle tissues in images of beef carcass ribeyes. T. ASAE, 33(6): 2059-2065.
    
21. Meng, X.Y., Y.H. Sun and X.D. Wang, 2010. Methods of extraction and analysis of grading features of rib-eye section of beef carcass. J. Jilin Univ., Eng. Technol. Edn., 40(2): 485-490, (In Chinese).
    
22. Qiu, J., M. Shen and Z. Peng, 2010. Beef marbling extraction based on modified fuzzy C-means clustering algorithm. T. Chinese Soc. Agric. Mach., 41(8): 184-188.
    
23. Zhang, Y.J. and J.J. Gergrands, 1992. Segmentation evaluation using ultimate measurement accuracy. Proceeding of SPIE 1657, Image Processing Algorithms and Techniques III, 1657: 449-460.
    
24. Zhao, J., M. Liu and H. Zhang, 2004. Segmentation of longissimus dorsi and marbling in ribeye imaging based on mathematical morphology. T. Chinese Soc. Agric. Eng., 20(1): 143-146, (In Chinese).
    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.