Automatic Recognition of Pollutants in Packaged Foods from x-ray Imaging

Giorgio Grasso, Rosa Maria Gembillo, Maria Schepis

Abstract

The quality and purity of industrially packaged foods is today of fundamental importance, given the level of expectation of consumers and the current laws imposing serious liabilities on producers. This paper presents a novel method for automatic recognition of pollutants in packaged foods for industrial applications. To maximize the contrast between foods and pollutants a dual acquisition method has been applied to obtain a pair of images taken at two different x-ray source voltages. Taking advantage from the wavelength dependence of absorption coefficient for different materials. In order to further increase the classification potential of the algorithms, the Hε color spectrum was adopted, for its high discrimination capabilities. The analysis of images is performed on-line utilizing three independent methods.Over a series of experiments each of the three strategies have given a correct classification rate of pollutants ranging from 83% to 95%. To further increase the degree of reliability of the automatic recognition process, the three methods have been combined into a pollution coefficient. The confidence achieved on the experimental set resulted in a 92% correct classifications, for pollutants larger than 2mm.

References

  1. Casasent, D., Sipe; M.A., Schatzky, T.F., Keagy, P.M., Lee, L.L.: Neural Net Classification of X-Ray Pistachio Nut Data, Lebensm.-Wiss. u.-Technol. 31 (1998) 122-128
  2. Casasent, D. Talukder, A., Lee, H.W.: X-Ray Agricultural Product Inspection: Segmentation and Classification, In: Proc. SPIE 3205 (1997) 46-55
  3. Keagy, P.M., Schatzky, T.: Machine Recognition of Weevil Damage in Wheat Radiograph, Cereal Chemistry 70 (1993) 696-700
  4. Subbiah, J., Kranzler, G., Kotwaliwale, N., Weckler, P.: Predicting Beef Tenderness using Dual Energy X-ray Absorption, Biosystems & Agricultural Engineering Oklahoma State University, Internal Report (2002)
  5. Bini, D., Capovani, M., Menchi, O.: Metodi numerici per l'algebra lineare, Zanichelli, Bologna (1993)
  6. Abeasis, S.: Algebra lineare e geometria, Zanichelli, Bologna, (1994)
  7. Gonzalez, R.C., Woods, R.E.: Digital image processing Second Edition, Prentice Hall, New York (2001)
  8. Grasso, G., Recce, M.: Scene analysis for an orange picking robot. In: Proc. 6th Inter. Congress for Computer Technology in Agriculture (ICCTA'96) eds. C. Lokhorst, A.J. Udink ten Cate, and A.A. Dijkhuizen, VIAS, The Netherlands (1996) 275-280
  9. Plebe, A., Grasso, G.: Localization of spherical fruits for robotic harvesting. Machine Vision and Applications, 13(2) (2001) 70-79
  10. Rosemblatt F.: The Perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 56 (1958) 386-408
  11. Rumelhart D. E., Hinton G. E., Williams R.J.: Learinig representations by backpropagating errors, Nature 323 (1986) 533-536
  12. Bose, N.K., Liang, P.: Neural Networks Fundamentals with Graphs, Algorithms, and Applications, McGraw-Hill, International Editions, Singapore (1996)
  13. MacQueen, J.: Some method for classification and analysis of multi-variate observation. In: Proc. Of the Fifth Berkeley Symp on Math., Statistic and Probability, LeCam, L. M. and Neyman, J, (eds.), Berkeley: U. California Press, 281 (1967)
  14. Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. On PAMI, 16(6) (1994) 641- 647
Download


Paper Citation


in Harvard Style

Grasso G., Maria Gembillo R. and Schepis M. (2005). Automatic Recognition of Pollutants in Packaged Foods from x-ray Imaging . In Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2005) ISBN 972-8865-28-7, pages 63-72. DOI: 10.5220/0002542100630072


in Bibtex Style

@conference{pris05,
author={Giorgio Grasso and Rosa Maria Gembillo and Maria Schepis},
title={Automatic Recognition of Pollutants in Packaged Foods from x-ray Imaging},
booktitle={Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2005)},
year={2005},
pages={63-72},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002542100630072},
isbn={972-8865-28-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2005)
TI - Automatic Recognition of Pollutants in Packaged Foods from x-ray Imaging
SN - 972-8865-28-7
AU - Grasso G.
AU - Maria Gembillo R.
AU - Schepis M.
PY - 2005
SP - 63
EP - 72
DO - 10.5220/0002542100630072