M. Shiraishi et H. Sumiya, PLANT-IDENTIFICATION FROM LEAVES USING QUASI-SENSOR FUSION, Journal of manufacturing science and engineering, 118(3), 1996, pp. 382-387
The method described here identifies plants by using a machine vision
technique. This method achieves effective image detection independent
of surrounding conditions, dimensionless image detection in each growt
h stage, and determination of the critical factor for discriminating i
ndividual plants. These are the fundamental factors for successful aut
omatic thinning, cropping, weeding, and harvesting using intelligent a
gricultural robots. Color, aspect ratio, size, radius permutation in l
eaf profiles, complexity, and curvature are used to classify each plan
t. Effective discrimination is obtained by using a quasi-sensor fusion
combined with a total occurrence range for decision making.