Articles
QUALITY ASSESSMENT OF SLICED CHESTNUT (CASTANEA SPP.) USING COLOR IMAGES
Article number
1019_11
Pages
73 – 80
Language
English
Abstract
Unbiased internal quality classification of chestnuts (Castanea spp.) is extremely important to the fresh and processed industries.
In addition, it can be used as a tool for applied scientific studies, such as the training of non-invasive techniques to determine chestnut internal quality and the effect of pre- and post-harvest treatments.
Currently, humans visually perform the invasive quality assessment of chestnuts.
This procedure is prone to errors due to individuals fatigue, lack of training, and subjectivity.
Thus, a technique that can objectively classify internal quality of chestnuts needs to be developed.
In this paper, a computer vision methodology is proposed to sort chestnuts into five classes, as established by an expert human rater.
Color images from slices with different quality classes were acquired, using a flat panel scanner, from the hybrid cultivar Colossal and Chinese chestnut (Castanea mollissima) seedlings.
Results showed that the proposed technique is accurate (performance accuracy of 89.6%), reliable and objective.
It is a useful tool to determine chestnut slice quality and might be applicable to automated in-line sorting systems.
In addition, it can be used as a tool for applied scientific studies, such as the training of non-invasive techniques to determine chestnut internal quality and the effect of pre- and post-harvest treatments.
Currently, humans visually perform the invasive quality assessment of chestnuts.
This procedure is prone to errors due to individuals fatigue, lack of training, and subjectivity.
Thus, a technique that can objectively classify internal quality of chestnuts needs to be developed.
In this paper, a computer vision methodology is proposed to sort chestnuts into five classes, as established by an expert human rater.
Color images from slices with different quality classes were acquired, using a flat panel scanner, from the hybrid cultivar Colossal and Chinese chestnut (Castanea mollissima) seedlings.
Results showed that the proposed technique is accurate (performance accuracy of 89.6%), reliable and objective.
It is a useful tool to determine chestnut slice quality and might be applicable to automated in-line sorting systems.
Publication
Authors
I.R. Donis-González, D.E. Guyer, J. Burns, G.A. Leive-Valenzuela
Keywords
classification, computer vision, pattern recognition, processed chestnuts
Online Articles (40)