SUCCESSIVE PROJECTIONS ALGORITHM-MULTIVARIABLE LINEAR REGRESSION (SPA-MLR) CLASSIFIER FOR THE DETECTION OF CONTAMINANTS ON CHICKEN CARCASSES IN HYPERSPECTRAL IMAGES

During slaughtering and further processing, chicken carcasses are inevitably contaminated by microbial pathogen contaminants. Due to food safety concerns, many countries implement a zero-tolerance policy that forbids the placement of visibly contaminated carcasses in ice-water chiller tanks during processing. Manual detection of contaminants is labor consuming and imprecise. Here, a successive projections algorithm (SPA)-multivariable linear regression (MLR) classifier based on an optimal performance threshold was developed for automatic detection of contaminants on chicken carcasses. Hyperspectral images were obtained using a hyperspectral imaging system. A regression model of the classifier was established by MLR based on twelve characteristic wavelengths (505, 537, 561, 562, 564, 575, 604, 627, 656, 665, 670, and 689 nm) selected by SPA, and the optimal threshold T = 1 was obtained from the receiver operating characteristic (ROC) analysis. The SPA-MLR classifier provided the best detection results when compared with the SPA-partial least squares (PLS) regression classifier and the SPA-least squares supported vector machine (LS-SVM) classifier. The true positive rate (TPR) of 100% and the false positive rate (FPR) of 0.392% indicate that the SPA-MLR classifier can utilize spatial and spectral information to effectively detect contaminants on chicken carcasses.

основанный на алгоритме последовательных проекций и многомерной линейной регрессии классификатор, рабочая характеристика приемника, гиперспектральное изображение, куриная тушка, обнаружение загрязняющих веществ, SPA-MLR classifier, ROC analysis, hyperspectral imaging, chicken carcass, contaminant detection

1. http://www.consumerreports.org/cro/magazine/2014/02/the-high-cost-of-cheap-chicken/index.htm (2014).

2. F. Lawrence, A. Wasley, and R. Ciorniciuc, The Guardian (2014); http://www.theguardian.com/world/2014/jul/23/-sp-revealed-dirty-secret-uk-poultry-industry-chicken-campylobacter.

3. USDA, Final rule.9CFR part 304. Fed. Regist., 61, 38805-38989 (1996).

4. W. R. Windham, D. P. Smith, B. Park, K. C. Lawrence, P. W. Feldner, Trans. ASAE, 46, 1733-1738 (2003).

5. Y. R. Chen, W. R. Hruschka, H. Early, J. Food Process Eng., 23, 89-99 (2000).

6. Z. Xiong, D.W. Sun, A. Xie, Z. Han, L. Wang, Food Chem., 175, 417-422 (2015).

7. S. A. Hawkins, B. Bowker, H. Zhuang, G. Gamble, R. Holser, J. Food Res., 3, 57-65 (2014).

8. D. Alexandrakis, G. Downey, A. G. M. Scannell, Food Bioprocess Tech., 5, 338-347 (2012).

9. B. Park, K. C. Lawrence, W. R. Windham, R. J. Buhr, Trans. ASAE, 45, 2017-2026 (2002).

10. B. Park, K. C. Lawrence, W. R. Windham, D. P. Smith, J. Food Eng., 75, 340-348 (2006).

11. B. Park, S.-C. Yoon, W. R. Windham, K. C. Lawrence, M. S. Kim, K. Chao, Sens. Instrum. Food Qual. Saf., 5, 25-32 (2011).

12. W. R. Windham, D. P. Smith, M. E. Berrang, K. C. Lawrence, P. W. Feldner, Int. J. Poult. Sci., 4, 657-662 (2005).

13. W. Wu, G. Y. Chen, J. C. Xia, C.W. Ye, K. J. Chen, Spectrosc. Spect. Anal., 34, 3363-3367 (2014).

14. S. C. Yoon, B. Park, K. C. Lawrence, W. R. Windham, G. W.Heitschmidt, Comput. Electron. Agric., 79, 159-168 (2011).

15. G. W. Heitschmidt, B. Park, K.C. Lawrence, W. R. Windham, D. P. Smith, Trans. ASABE, 50, 1427-1432 (2007).

16. S. Kang, K. Lee, J. Son, M. S. Kim, Proc. Food Sci., 1, 953-959 (2011).

17. K. C. Lawrence, W. R. Windham, B. Park, R. J. Buhr, J. Near Infrared Spectrosc., 11, 269-281 (2003).

18. C. D. Everard, M. S. Kim, H. Lee, J. Food Eng., 143, 139-145 (2014).

19. M. C. U. Araújo, T. C. B. Saldanha, R. K. H. Galvão, T. Yoneyama, H. C. Chame, V. Visani, Chemometr. Intell. Lab. Syst., 57, 65-73 (2001).

20. R. K. H. Galvão, M. C. U. Araújo, W. D. Fragoso, E. C. Silva, G. E. José, S. F. C. Soares, H. M. Paiva, Chemometr. Intell. Lab. Syst., 92, 83-91 (2008).

21. C. E. Metz, Semin. Nucl. Med., 8, 283-298 (1978).

22. L. D. Stefano, A. Bulgarelli, Int. Conf. Image Anal. Process., 322-327 (1999).