ศูนย์นวัตกรรมเทคโนโลยีหลังการเก็บเกี่ยว

Evaluating tomato ripeness using a neural network.

Shibata, T.; Iwao, K.; Takano, T.;

Journal of Society of High Technology in Agriculture Year: 1996 Vol: 8 Issue: 3 Pages: 160-167 Ref: 16 ref.

1996

บทคัดย่อ

A method for evaluating tomato ripeness, utilizing its surface colour, was developed using a machine vision system with colour image processing capability and a multi layered neural network-based software system. The tomato ripeness was classified into 4 categories: unripe, half ripe, fully ripe and over ripe according to the standard commercial classification for manual sorting. Over ripe means the fruit has lost its freshness. Three colour specification values, i.e. lightness L, chroma C and hue H were calculated from the RGB gray levels of a captured colour digital image of a tomato by an on-line image processing system. Only 0.2-0.5% of the total surface area of a fruit is needed for colour image sensing of the classification. The area size representing 0.5% of the total area was covered by 243 pixels of resolution. A 3-layered neural network with 4 hidden layer units gave a satisfactory performance at 18 000 times BP (Back Propagation) learning. The total processing time from image capture

to output for a single fruit was 0.45 seconds. The recognition rate for the ripeness classification using this method was as high as 93%. A recognition rate of only 77% was obtained by the multiple regression model tested. The present work provides another example to strengthen the area of neural network application research on machine vision systems including agricultural robotics, postharvest, and processing systems.