Abstract:
Using image recognition technology can greatly improve the efficiency of fruit automatic grading. This paper proposes a fruit grading algorithm based on simulated annealing algorithm and neural network. When the BP neural network model is used to attain the optimal solution, it is easy to fall into the local optimal solution. In order to solve this problem, the simulated annealing algorithm is introduced to expand the weight of updated space of the network. In this paper, apple is selected as the research object. Firstly, the feature model for Apple classification is established, and then the corresponding BP neural network model is established. Finally, the simulated annealing algorithm is used to optimize the neural network algorithm. Compared with the common BP neural network algorithm and RBF neural network algorithm, this algorithm has better recognition efficiency.