<![CDATA[Differences in the type of papaya fruit and the level of maturity of ripe and unripe papayas can be seen from the color, texture and shape. Manually, consumers can check by looking at the condition of the papaya fruit based on its distinguishing characteristics. This manual method can of course produce different conclusions for each person. Errors also often occur because this manual method is very dependent on understanding the characteristics of papaya fruit and the level of accuracy. Therefore, we need a system that can classify the type and level of maturity automatically. In this research, a system is developed that can classify types and levels of maturity based on color, texture and shape features using the Support Vector Machine (SVM) method. The statistical approach method and the GLCM method are used in the feature extraction process. Color features in the HSI and YCbCr color spaces, texture features with GLCM and Horizontal Vertical Projection Integral shape features. The total data used in this study were 600 images of papaya fruit which were divided into training data and test data. The highest accuracy for the Bangkok dataset is obtained on the HSI feature, which is 66%, while for the California dataset it is obtained on the HSI feature, which is 65%.]]>
Copyrights © 2022
