Bibliographic citations
Bazán, K., Cotrina, C. (2018). Comparación de tres sistemas expertos y diferentes espacios de color en la clasificación del grado de madurez de frutos de aguaymanto (PHYSALIS PERUVIANA L.) [Tesis, Universidad Privada del Norte]. https://hdl.handle.net/11537/13467
Bazán, K., Cotrina, C. Comparación de tres sistemas expertos y diferentes espacios de color en la clasificación del grado de madurez de frutos de aguaymanto (PHYSALIS PERUVIANA L.) [Tesis]. PE: Universidad Privada del Norte; 2018. https://hdl.handle.net/11537/13467
@misc{renati/514947,
title = "Comparación de tres sistemas expertos y diferentes espacios de color en la clasificación del grado de madurez de frutos de aguaymanto (PHYSALIS PERUVIANA L.)",
author = "Cotrina Bazán, Carlos Adrián",
publisher = "Universidad Privada del Norte",
year = "2018"
}
ABSTRACT The classification of fresh fruits according to their ripeness is commonly a subjective and tedious task; consequently, there is growing interest in the use of non-contact techniques as such those based on computer vision and machine learning. In this paper, we propose the use of non-intrusive techniques for the classification of Cape gooseberry fruits. The proposal is based on the use of machine learning techniques combined with different color spaces. Given the success of techniques such as artificial neural networks, support vector machines, decision trees, and Knearest neighbors in classification problems, we decided to use these approaches in this research work. A sample of 819 Cape gooseberry fruits was obtained, and fruits were classified manually according to their level of ripeness in seven different classes. Images of each fruit were acquired in the RGB format through a system developed for this purpose. These images were preprocessed, filtered and segmented until the fruits were identified. For each piece of fruit, the median color parameter values in the RGB space were obtained, and these results were subsequently transformed into the HSV and L*a*b* color spaces. The values of each piece of fruit in the three color spaces and their corresponding degrees of ripeness were arranged for use in the creation, validation, and comparison of the developed classification models. The choice of color space was found to affect the quality of the classifier. Decision trees based systems offer the best results, the precision of these where higher than 97% when using 18 parameters and 6 parameters of interest, and higher than 72% when combined with RGB, HSV and L*a*b* color spaces. The artificial neural network-based models obtain more variable results. The models based on the L*a*b* color space offer the best results, the precision of these where superior than 72%. Finally, the model that best classifies the cape gooseberry fruits based on ripeness level is that resulting from the combination of the SVM technique and the RGB color space, obtaining an F measure of 79,47% and accuracy of 79,79%. KEYWORDS: Golden Berry, color spaces, artificial neural networks, support vector machines, decision trees, K-nearest neighbors.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.