GROWTH PREDICTION OF LETTUCE PLANTS BY IMAGE PROCESSING

Fresh weight of lettuce plants (Lactuca sativa L. non-heading type) was estimated by the automatic plant growth monitoring system with a personal computer for measuring and evaluating the plant growth. The image processing of plant growth is an effective tool for intact and non-destructive measurement, so as to be able to digitize continuously the images of plant or leaves with the computer system.

Growth curves of leaf area, fresh- and dry-weight of above ground parts from sowing to about 30 days in age showed an exponential pattern. Correlation coefficients between age in days after sowing and each growth index were 0.99 or higher. During the early growth period from two- to six-leaf stage, correlation coefficient between horizontal projected leaf area and top fresh weight was highest. i.e. 0.96 or higher. From these, top fresh weight is given accurately as the function of horizontal projected leaf area.

Correlation coefficients between top fresh weight at 30 days after sowing and estimated value from horizontal projected leaf area were 0.803–0.841. On the other hand, correlation coefficients obtained from growth rate by the regression curve were 0.709–0.736. Further, multiple correlation coefficients were 0.895–0.925, where the initial leaf area and growth rate of exponential regression curve were regarded as describing parameter.

In conclusion, the growth of lettuce plant was represented quantitatively as the function of horizontal projected leaf area by image processing.