Study on Recognition of Fertilized Chicken Eggs based on Particle Swarm Optimized Neural Network

In order to detect fertilized chicken eggs nondestructively to improve hatching rate, this paper uses the method of image processing and optimizing BP neural network by particle swarm to identify fertilized chicken eggs. Firstly, we use image collection device to collect images of the unfertilized and fertilized chicken eggs, to extract the feature of egg image, and then determine the input and output vector, while optimized neural network by particle swarm is 5 dimensional input and 1 dimensional outputs. Finally, we use particle swarm algorithm to optimize the weights and threshold of neural network, which can be used to predict the condition of fertilization. The experiment shows that, compared with the traditional BP neural network, it is more accurate to recognize the fertilized chicken eggs when using optimized BP neural network by particle swarm. The rate can reach 98.21%, which meets the requirements of recognizing fertilized chicken eggs.