Abstract:
Among the different classes of physical properties
of foods, color is considered the most
important visual attribute in quality perception. C
onsumers tend to associate color with
quality due to its good correlation with physical,
chemical and sensorial evaluations of
food quality. This study used an inexpensive method
to predict sweet cherries color
parameters by combining image processing and artifi
cial neural network (ANN)
techniques. The color measuring technique consisted
of a CCD camera for image
acquisition, MATLAB software for image analysis, an
d ANN for modeling. To
demonstrate the usefulness of this technique, chang
es of cherry color during ripening
were studied. After designing, training, and genera
lizing several ANNs using Levenberg-
Marquardt algorithm, a network with 7-14-11-3 archi
tecture showed the best correlation
(R
2
= 0.9999) for
L*, a*
and
b*
values from Chroma meter and the machine vision sy
stem.
L*
and
b*
parameters decreased during ripening of cherries a
nd
a*
parameter increased
at first and then decreased. Evaluation of
L*
,
a*
and
b*
values showed the possibility of
reliable use of this system for determination of ab
solute color values of foodstuffs with a
much lower cost in comparison with Chroma meter.
Keywords:
Cherry fruit, Color parameters
L
,
a
and
b
, Modeling.