Limits...
Sorting Olive Batches for the Milling Process Using Image Processing.

Aguilera Puerto D, Martínez Gila DM, Gámez García J, Gómez Ortega J - Sensors (Basel) (2015)

Bottom Line: The feature vector of the samples has been obtained on the basis of the olive image histograms.Moreover, different image preprocessing has been employed, and two classification techniques have been used: these are discriminant analysis and neural networks.The proposed methodology has been validated successfully, obtaining good classification results.

View Article: PubMed Central - PubMed

Affiliation: ANDALTEC, Plastic Technological Center, Martos, Jaén 23600, Spain. aguilera@andaltec.org.

ABSTRACT
The quality of virgin olive oil obtained in the milling process is directly bound to the characteristics of the olives. Hence, the correct classification of the different incoming olive batches is crucial to reach the maximum quality of the oil. The aim of this work is to provide an automatic inspection system, based on computer vision, and to classify automatically different batches of olives entering the milling process. The classification is based on the differentiation between ground and tree olives. For this purpose, three different species have been studied (Picudo, Picual and Hojiblanco). The samples have been obtained by picking the olives directly from the tree or from the ground. The feature vector of the samples has been obtained on the basis of the olive image histograms. Moreover, different image preprocessing has been employed, and two classification techniques have been used: these are discriminant analysis and neural networks. The proposed methodology has been validated successfully, obtaining good classification results.

No MeSH data available.


(a) Linear classification results without the ANOVA component filter; (b) linear classification results with the ANOVA component filter; (c) ANN classification results without the ANOVA component filter; (d) ANN classification results with the ANOVA component filter.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541852&req=5

f11-sensors-15-15738: (a) Linear classification results without the ANOVA component filter; (b) linear classification results with the ANOVA component filter; (c) ANN classification results without the ANOVA component filter; (d) ANN classification results with the ANOVA component filter.

Mentions: On the other hand, the classification results obtained with the linear classification algorithm (FDA) denote that it is a good approach to classify olive batches. These results were expected, because the PCA scores with the three principal components are almost separable with a plane (see Figure 11). In this case, the best result was reached with 15 PCA components, the three channels and the feature selection algorithm.


Sorting Olive Batches for the Milling Process Using Image Processing.

Aguilera Puerto D, Martínez Gila DM, Gámez García J, Gómez Ortega J - Sensors (Basel) (2015)

(a) Linear classification results without the ANOVA component filter; (b) linear classification results with the ANOVA component filter; (c) ANN classification results without the ANOVA component filter; (d) ANN classification results with the ANOVA component filter.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541852&req=5

f11-sensors-15-15738: (a) Linear classification results without the ANOVA component filter; (b) linear classification results with the ANOVA component filter; (c) ANN classification results without the ANOVA component filter; (d) ANN classification results with the ANOVA component filter.
Mentions: On the other hand, the classification results obtained with the linear classification algorithm (FDA) denote that it is a good approach to classify olive batches. These results were expected, because the PCA scores with the three principal components are almost separable with a plane (see Figure 11). In this case, the best result was reached with 15 PCA components, the three channels and the feature selection algorithm.

Bottom Line: The feature vector of the samples has been obtained on the basis of the olive image histograms.Moreover, different image preprocessing has been employed, and two classification techniques have been used: these are discriminant analysis and neural networks.The proposed methodology has been validated successfully, obtaining good classification results.

View Article: PubMed Central - PubMed

Affiliation: ANDALTEC, Plastic Technological Center, Martos, Jaén 23600, Spain. aguilera@andaltec.org.

ABSTRACT
The quality of virgin olive oil obtained in the milling process is directly bound to the characteristics of the olives. Hence, the correct classification of the different incoming olive batches is crucial to reach the maximum quality of the oil. The aim of this work is to provide an automatic inspection system, based on computer vision, and to classify automatically different batches of olives entering the milling process. The classification is based on the differentiation between ground and tree olives. For this purpose, three different species have been studied (Picudo, Picual and Hojiblanco). The samples have been obtained by picking the olives directly from the tree or from the ground. The feature vector of the samples has been obtained on the basis of the olive image histograms. Moreover, different image preprocessing has been employed, and two classification techniques have been used: these are discriminant analysis and neural networks. The proposed methodology has been validated successfully, obtaining good classification results.

No MeSH data available.