A NEW TECHNIQUE FOR GRAPE INSPECTION AND SORTING CLASSIFICATION

Document Type : Original Article

Authors

Agricultural Engineering Research Institute, Nadi Elsaid St., Dokki, Giza, Egypt

Abstract

Sorting and classification of fruits are the main problem specially for Superior
and King Ruby varieties which represent more than 50% of grape production in
Egypt. A usual procedure to carry out this task is based on human visual inspection
considering general fruit attributes like color, size, shape, firmness and sugar content
of grape cluster. Color contains important information about fruit status and in some
cases it is decisive for fruit quality differences. This paper provides a new technique
to investigate the applicability of color classification, sugar content and firmness of
grape. Standard RGB color chart, artificial neural network and a potential of nearinfrared
(NIR) reflectance as a means for nondestructive measurements of grape
firmness and sugar content were used. NIR spectral data were collected from the two
varieties of grape in the spectral region between 800 nm and 1700 nm. Statistical
models were developed using the partial least square method to predict the firmness
and sugar content of grape. The models gave relatively good predictions of the
firmness of both Superior and King Ruby, with corresponding r values of 0.80 and
0.65. The NIR models gave excellent prediction for grape sugar content with values
of 0.71 % and 0.65 % Brix for Superior and King Ruby, respectively.

Keywords

Files

Share

How to cite

Statistics