A Convolutional Neural Network for Airport Security Inspection of Dangerous Goods

Abstract

According to the problems of heavy workload, low efficiency, easy fatigue misjudgement with artificial recognition and imbalance of dangerous goods image dataset in airport security inspection caused the low recognition accuracy, a convolution neural network automatic recognition model based on oversampling for dangerous goods is proposed. Firstly, the oversampling technique is used to equalize the dataset of dangerous goods image, and then the image is inputted into the convolution neural network model composed of four convolution layers and one full-connection layer for training. The stochastic deactivation optimization technique is introduced in the training to get better recognition effect. The experimental results on a dangerous goods image dataset of public security in 2017 show that the recognition accuracy of the model can reach 90.7% after equalization, which is 33.4% higher than that before equalization. In addition, the recognition accuracy of the model is 5.8%, 7.2% and 5.4% higher than that of GoogleLeNet, AlexNet and ResNet respectively. The model has high recognition accuracy and good real-time performance, which is of positive significance to improve the level of airport security intelligence.