Title :
Application of computer vision and Support Vector Machines to estimate the content of impurities in olive oil samples
Author :
Marchal, P. Cano ; Gila, D. Martinez ; Garcia, J. Gamez ; Ortega, J.G.
Author_Institution :
Autom. & Comput. Vision Group, Univ. of Jaen, Jaen, Spain
Abstract :
The determination of the content of impurities is a very frequent analysis performed on virgin olive oil samples, but the official method established in the European norm CE 2568/91 is quite work-intensive, and it would be convenient to have an alternative approximate method to evaluate the performance of the impurity removal process. In this work we develop a system based on computer vision and pattern recognition to classify the content of impurities of the olive oil samples in three sets, indicative of the goodness of the separation process of olive oil after its extraction from the paste. Starting from the histograms of the channels of the RGB, CIELAB and HSV color spaces, we construct an initial input parameter vector and perform a feature extraction previous to the classification. Several linear and non-linear feature extraction techniques were evaluated, and the classifiers used were Support Vector Machines. The best classification rate achieved was 87.66%, obtained using KPCA and a grade-3-polynomial kernel SVM.
Keywords :
computer vision; feature extraction; image classification; image colour analysis; impurities; principal component analysis; production engineering computing; separation; support vector machines; vegetable oils; CIELAB color spaces; European norm CE 2568/91; HSV color spaces; KPCA; RGB color spaces; approximate method; computer vision application; impurity content classification; impurity content estimation; impurity removal process; input parameter vector; non-linear feature extraction techniques; olive oil separation process; pattern recognition; support vector machines; virgin olive oil samples; Feature extraction; Histograms; Impurities; Kernel; Principal component analysis; Support vector machine classification; Olive oil analysis; Support Vector Machines; computer vision;
Conference_Titel :
Automation and Computing (ICAC), 2012 18th International Conference on
Conference_Location :
Loughborough
Print_ISBN :
978-1-4673-1722-1