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.


Neuronal network diagram where P is the input vector; IW is the input weights; OW is the output weights; b1 and b2 are the bias; f1 and f2 are the sigmoid functions; and C is the classification result.
© Copyright Policy
Related In: Results  -  Collection

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

f6-sensors-15-15738: Neuronal network diagram where P is the input vector; IW is the input weights; OW is the output weights; b1 and b2 are the bias; f1 and f2 are the sigmoid functions; and C is the classification result.

Mentions: Only one hidden layer was considered, since this configuration is capable of learning any pattern and less prone to getting caught in local minima in those networks with a higher number of hidden layers [39]. The number of input nodes was the same as vector components selected in the previous step. Furthermore, the neural network was tested with different numbers of neurons in the hidden layer. The classification results were similar; therefore, one neuron was established. Finally, the output layer was configured with one neuron, because it is sufficient to classify between soil and tree classes. Figure 6 shows the net topology that has been employed.


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)

Neuronal network diagram where P is the input vector; IW is the input weights; OW is the output weights; b1 and b2 are the bias; f1 and f2 are the sigmoid functions; and C is the classification result.
© Copyright Policy
Related In: Results  -  Collection

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

f6-sensors-15-15738: Neuronal network diagram where P is the input vector; IW is the input weights; OW is the output weights; b1 and b2 are the bias; f1 and f2 are the sigmoid functions; and C is the classification result.
Mentions: Only one hidden layer was considered, since this configuration is capable of learning any pattern and less prone to getting caught in local minima in those networks with a higher number of hidden layers [39]. The number of input nodes was the same as vector components selected in the previous step. Furthermore, the neural network was tested with different numbers of neurons in the hidden layer. The classification results were similar; therefore, one neuron was established. Finally, the output layer was configured with one neuron, because it is sufficient to classify between soil and tree classes. Figure 6 shows the net topology that has been employed.

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.