<![CDATA[Identification of passion fruit maturity is still done manually by the farmers . Fruit was seen visually and responded by the brain to differentiate maturity levels . In large amounts it would be difficult to maintain their performance. This study was a non-conventional method of measurement that used digital image processing to produce data that would be processed by artificial neural network and then processed using computer software that could be used to determine passion fruit maturity level. Passion fruit was identified based on the histrogram input image color ( RGB ) that was obtained from the results of the capture program built using Visual Basic. Some sample of the passion fruit learning pattern data had different weight values as input to the neural network using backpropagation method to distinguish raw, ripe and half ripe fruits. This identification system was capable to identify the entire category of fruit which was 94,4 % correct identification. From the identification results that had been done, the identification of the three outputs were 100 % ripe, half ripe 83,3 % , and 100 % raw passion fruit . Results of the identifications were affected by the fruit shooting process. Key words : Artificial Neural Network, Back Propagation, Identification, Image Processing, Passion Fruit]]>
Copyrights © 2015
