A New Few-Shot Learning-Based Model for Prohibited Objects Detection in Cluttered Baggage X-Ray Images Through Edge Detection and Reverse Validation

Detecting prohibited items via X-ray screening at airports and sensitive venues is essential for preventing smuggling and breaches of security. The difficulty in prohibited items inspection lies in accurately detecting prohibited items in complex X-ray images and limited access to X-ray images containing prohibited items. Few-shot detection aims at learning with limited examples and assigning a category label to each object. However, most few-shot learning methods do not focus on the edge information of the occluded object in X-ray images, which is crucial for the model to detect prohibited items in the X-ray images. In this paper, we presents a method (RVViT) for few-shot prohibited items detection tasks which fully acknowledges the significance of X-ray penetrability and increases the stability of few-shot learning model. Specifically, a Transformer encoder is firstly adopted for generating high-level semantic features that contain global information. At the same time, an edge detection module is devised for enhancing the edge information of prohibited items. Moreover, to further improve the stability of the few-shot learning model and ensure prototype consistency between the support and query samples, a reverse validation strategy is proposed to assist training. Extensive experiments demonstrate our method outperforms state-of-the-art approaches in terms of detection with a small number of samples.