IDENTIFIKASI MUTU FISIK JAGUNG DENGAN MENGGUNAKAN PENGOLAHAN CITRA DIGITAL DAN JARINGAN SYARAF TIRUAN

Physical quality factors are the main problems in the dried seed corn production. Determination of physical quality is usually carried out visually by the persons who have expertise related to their experiences. This method is exhaustive and imprecise since it is influenced by human fatigue. The objective of this research is to identify the physical quality of seed corn by using the digital image processing and artificial neural network (ANN). The image of seed corn was taken by using digital camera and processed by image processing program. ANN model was developed with 10 input parameters, 20 hidden layers and 4 targets. The fourth targets were whole seed, damaged seed, broken seed and mouldy seed. The accuracy of the model was 95%.