| Summary: | Indonesia has a great potency on horticultural commodity, such as
tomatoes . The high rate demand of tomatoes, both within and outside the country,
raising the need for ensuring the quality of the tomatoes. Tomato maturity level is
one of determining factor for quality. Identification process of tomatoes maturity
is generally dependent on the human perception of color indicator, which is
subjective and took a long time. Color indicator is one of the characteristics of
tomatoes maturity. The development of the image processing system, which is
combine with artificial neural network (ANN) method to apply, allowing the
identification of tomatoes maturity level more accurately and quickly.
Digital image processing refers to two-dimensional images processing
using a computer. ANN is a computational system which the architecture and
operation system inspired by the knowledge about the biological neuron cells in
brain. The tools used are Box Machine Vision and MATLAB 2012, while the
material is red tomato. Number of sample is 48 tomatoes which divided into 2
groups, 30 tomatoes as training data and 18 tomatoes to testing the network.
Image capturing of each sample conducted on each of four sides. The parameters
used as input to the ANN is mean Red, mean Green, mean Blue and correlation.
The results of this study show that, with combining image processing and
artificial neural network method, maturity level identification of red tomatoes
veriety based on USDA standard (green, breaker, turning, pink, light red, and red)
can be successfully done. ANN architecture consisted of four cells
|
|---|