The realization of project enclosed construction and training neuronal model to identification of damages of corn kernels. Recognizing the damages was made on basis of digital photos converted by produced computer system to learning files dedicated for artificial neural network. The network was learned on chosen representative tags. The taught model marks abilities of identification approximate quality to human. Neural model can in real time identify larger number of kernels than man. The number of kernels is only limited by method of images acquisition and the computational power of applied equipment to implementation of model. Big advantage is also the lack of natural man limitations which for example are: fatigue and subjective opinion.