Grain Sample Quality Assessment Fusing the Results from Color Image and Spectra Analyses

M. I. MLADENOV1, M. P. DEJANOV2 and R. TSENKOVA3
1 University of Ruse, Department of Automatics and Mechatronics, BG – 7017 Ruse, Bulgaria
2 University of Ruse, Department of Automatics and Mechatronics, BG - 7017 Ruse, Bulgaria
3 Biomeasurement Technology Laboratory, Kobe University, Japan

Abstract

MLADENOV, M. I., M. P. DEJANOV and R. TSENKOVA, 2015. Grain sample quality assessment fusing the results from color image and spectra analyses. Bulg. J. Agric. Sci., 21: 225-236

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 theobject 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.

Key words: grain quality assessment, color image analysis, spectra analysis, classification, data fusion
Abbreviations: ANN – Artificial Neural Networks; CA - Cluster Analysis; CDRBE - classifier with decomposing RBEs; CRBEP - classifier with RBEs which takes into account the class potentials; CSRBE - classifier with standard RBEs; CVS – Computer Vision System; HIS - Hyperspectral Imaging System7; INTECHN – Intelligent Technologies for Assessment of Quality and Safety of Food Agricultural Products; KNN - K-Nearest Neighbors; LDA – linear discriminant analysis; NIR spectra analyses – Near infrared spectra analyses; NIRS - A NIR spectroscopy; PCA - Principle Component Analysis; QDA - quadratic discriminant analysis; RBEs - Radial Basis Elements; SIMCA - Soft Independent Modeling of Class Analogy; SVM - Support Vector Machines; VIS spectra analyses – Visible spectra analyses; 1cc – first color class; 1csh – first shape class; 1cst – first class standard

See the article as a PDF.