Studies on the measurement of the color of rice [Oryza sativa] leaves by image processing
1997
Okado, M. (Ishikawa Prefecture Coll. of Agriculture, Nonoichi (Japan))
In this study, an image processing system enabling to measure the color of rice leaves on rice fields was developed and tested. The correlation between the measured values by chlorophyllmeter and the density value of digital image of a rice leaf was discussed. As the result of this experiment, it was found that the chlorophyll content of rice leaves correlated with density values of Red and Green, and intensity value Y. When this system is used in actual rice fields, it is required to discriminate automatically between rice plants and the others on the image. Then a new image processing software was developed for this purpose. The neural network was applied to it. The correlation between the measured values by a chlorophyllmeter and RGB density values of digital images of rice communities was discussed. A multiple regression equation was calculated. When used in actual rice fields, this system was inferior to the chlorophyllmeter in the measurement accuracy, but was superior to the color scale. It was superior to the chlorophyllmeter in the reduction of the measuring time
显示更多 [+] 显示较少 [-]