抄録
The harvesting operation is a great burden for farmers. Workers need the reduction of the harvesting operation in the agriculture. Then, the purpose of this study is the construction of useful visual recognition system which requires in automation and robotization of harvesting operation .In this research, Eggplants are taken up as an example of agricultural objects for the search and searched using genetic algorithm from scene image. Many agricultural objects have been composed of curved surface. Therefore, It is proposed that the recognition technique of agricultural objects using the Neural-Networks which learned the change of luminance information. Through experimental results, it is shown that new technology proposed here is sufficiently valid on recognition for agricultural object.
