Identification of Citrus Maturity with Artificial Neural Network

Identification of citrus maturity is still done manually by the farmers. Fruit seen visually by eyes and responded by the brain to differentiate maturity level. In large amounts it would be difficult to maintain its performance. This study was a non-conventional method of measurement that used digital image processing to produce data that will be processed by artificial neural network and then processed using computer software that can be used to determine citrus maturity level. Citrus are identified based on the histrogram input image color ( RGB ) that obtained from the results of the capture program built by using Visual Basic. Some sample of the learning pattern citrus data had different weighted values as input to the neural network by using back propagation method to distinguish raw, ripe and over ripe fruits. This identification system was capable to identify the entire category of fruit which were 90 % correct identification. From the identification that had been done, resulting the identification of the three outputs 100 % ripe citrus, over ripe 80 %, and 100 % raw. Results of the identifications were affected by the shooting fruit process. Key words : Artificial Neural Network, Image processing, back propagation, Identification, citrus