LightRay: Lightweight network for prohibited items detection in X-ray images during security inspection.

Object detection algorithms based on deep learning have been widely used in the intelligent detection of prohibited items in X-ray images during the security inspection process. However, security inspection is a process that emphasizes timeliness, and the low inference efficiency brought by overly complex deep neural networks is not allowed. In this paper, we propose a lightweight object detection framework based on the YOLOv4 algorithm, named LightRay. Where MobileNetV3 is applied as the feature extraction backbone. To effectively deal with the detection problem of prohibited items with small sizes in complex backgrounds, a feature enhancement network in shallow layers is proposed. Where, the Lightweight Feature Pyramid Network (LFPN) and the Convolutional Block Attention Module (CBAM) effectively achieve feature fusion of different scales, while strengthening the features of small objects. The experimental results show that the mAP of the lightRay model is 87.28% on the SIXray data set, while the FLOPs of the model are reduced to the original 1/5, and Params is reduced to 1/3 of the original. In addition, some ablation experiments confirm the ability of the LightRay model the detection of prohibited items with small sizes. The codes of LightRay are released at https://github.com/zhg-SZPT/LightRay. [ABSTRACT FROM AUTHOR]