Modern Approaches for Grain Quality Analysis and Assessment
The paper presents the approaches, methods and tools for assessment of main quality features of grain samples which are based on color image and spectra analyses. Visible features like grain color, shape, and dimensions are extracted from the object images. Information about object color and surface texture is obtained from the object spectral characteristics. The categorization of the grain sample elements in three quality groups is accomplished using two data fusion approaches. The first approach is based on the fusion of the results about object color and shape characteristics obtained using image analysis only. The second approach fuses the shape data obtained by image analysis and the color and surface texture data obtained by spectra analysis. The results obtained by the two data fusion approaches are compared.
KeywordsLinear Discriminant Analysis Object Color Texture Model Quadratic Discriminant Analysis Sample Element
A big part of the analyses and results presented in this investigation are a part of implementation of the research project “Intelligent Technologies for Assessment of Quality and Safety of Food Agricultural Products”, funded by the Bulgarian National Science Fund.
- 3.C. Damyanov, Non Destructive Recognition of Quality in System for Food Products Automatic Sorting, Monography (Academic publishing of the University of Food Technologies, Plovdiv, 2006)Google Scholar
- 11.S. Mahesh, D.S. Jayas, J. Paliwal, N.D.G. White, Identification of western Canadian wheat classes at different moisture levels using near-infrared (NIR) hyperspectral imaging. CSBE Paper No. 08-196 (2008)Google Scholar
- 12.S. Mahesh, D.S. Jayas, J. Paliwal, N.D.G. White, Identification of wheat classes at different moisture levels using near-infrared hyperspectral images of bulk samples. Sens. Instrum. Food Qual. Saf. 2(3–4), 1007–1015 (2010)Google Scholar
- 16.M.I. Mladenov, Grain Quality Analysis and Assessment. (Monography, Academic publishing of the University of Ruse, Ruse, 2011)Google Scholar
- 17.M. Mladenov, Pattern classification in a noisy environment. Inf. Technol. Control 1(2011), 23–33 (2011)Google Scholar
- 18.M. Mladenov, M. Dejanov, Application of neural networks for seed germination assessment, in Proceedings of the 9th WSEAS International Conference on Neural Networks (2008), pp. 67–72Google Scholar
- 19.M. Mladenov, T. Draganova, M. Dejanov, S. Penchev, Assessment of grain quality features using image and spectra analyses, in Proceedings of the International IFAC Workshop DYCAF (Plovdiv, 2012), pp. 119–126Google Scholar
- 20.M. Mladenov, S. Penchev, M. Dejanov, M. Mustafa, Quality assessment of grain samples using colour image analysis, in Proceedings of the 8th IASTED International Conference on Signal Processing, Pattern Recognition and Applications (2011)Google Scholar
- 23.S. Ning, R. Ruan, L. Luo, X. Chen, P.L. Chen, R.K. Jones, Automation of a machine vision and neural network based system for determination of scabby rate of wheat samples. ASAE Annual International Meeting, Orlando, Florida (1988)Google Scholar
- 31.R. Ruan, Y. Li, X. Lin, P. Chen, Non-destructive determination of deoxynivalenol levels in barley using nea-infrared spectroscopy. Appl. Eng. Agric. 18(50), 549–553 (2002)Google Scholar
- 32.X14 30 S.H. Kutzbach, Determination of broken kernels in threshing process using image analysis and machine vision, in Proceedings of 27th Symposium “Actual Tasks on Agricultural Engineering”, Croatia (1999)Google Scholar
- 33.R. Tsenkova, H. Meilina, S. Kuroki, D. Burns, Near infrared spectroscopy using short wavelengths and leave-one-cow-out cross-validation for quantification of somatic cells in milk. J. Near Infrared Spectro. 17(6), 345–352 (2010)Google Scholar