Classification for the Ripeness of Papayas Using Artificial Neural Network (ANN) and Threshold Rule

The main objective of this project is developing the technique to classify the ripeness of papaya into 3 categories, which is immature, mature and over mature systematically based on their mean RGB value components. This system involved the process of collecting samples with different level of ripeness, image processing and image classification by using artificial neural network and threshold rule. Collecting papaya sample is done by using digital camera with 3.2 mega pixels. Image processing stage involves procedure such as edge detection, morphological operation and masking operation. 18 samples were used as training for artificial neural network. In order to see whether the both method mention above can classify the image correctly, another 32 images was used as testing. From the result obtained, it was shown that the artificial neural network can generally classify the ripeness of papaya better than threshold rule. This is because it can classify up to 30 samples correctly while threshold rule only 27 samples. Developing a program totally by using Matlab version 7.0 can help classification process successfully.