Open AccessThe Measurement Of Maturity Level In Chili’s Using Index Pixel
Author(s) -
Nurul Kusuma Delina,
Iis Hamsir Ayub Wahab,
Amal Khairan
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1569/2/022032
Subject(s) - ripeness , pixel , rgb color model , mathematics , hsl and hsv , artificial intelligence , computer science , computer vision , statistics , horticulture , ripening , virus , virology , biology
A lot of knowledge and techniques of image processing which are now available are widely various. Much research as well as development is conducted in terms of detecting ripe fruits, one of which is chili. It is one of the local commodities that is marketable. The process of being ripe chili is relatively fast. Generally, to measure ripeness is still carried out manually. The disadvantage of this method is that the level of accuracy is inconsistent, causing fruit decay in numbers. On behalf of lowering the risk of fruit decay, the research conducted uses index pixel method. This means itself is the normalization of variety illuminated by taking ratio in each group of smallest points in an image processing. In this study, the image taking of chili using box equipped with black background is confirmed to be useful in reducing time of segmentation process. When it is in the process of detecting image by searching for the average of index pixel, then RGB will be counted using Learning Vector Quantization (LVQ) that is the calculation utilizing weighing value. As a result, the classification of maturity level can be seen in the test with a very high percentage value and influence to detect fruit ripeness, signed by the color of RG pixels (red and green) by 94.9% correctly detected, the color pixel RB (red and blue) is quite influential by 93.9% correctly detected, and the color of the GB pixel (green and blue) which was less influential at 63.6% was correctly detected.