四川师范大学学报（自然科学版）2025，Vol.48Issue(2)：253-260,8.DOI:10.3969/j.issn.1001-8395.2025.02.010
基于改进YOLOv8的X线安检图像违禁品检测方法
A Contraband Detection Method for X-ray Security Images Based on Improved YOLOv8
摘要
Abstract
The efficiency of manual security checks is low and prone to errors.Implementing automatic security checks based on artificial intelligence is the development trend of security checks.The YOLOv8 object detection model has been improved to address the issues of low detection accuracy and high missed detection rate for a small number of categories in X-ray prohibited item detection.On the basis of YOLOv8n,the network structure was modified,attention mechanism was introduced,and a YOLOv8n-ECA object detec-tion model with Efficient Channel Attention(ECA)was proposed to better extract the features of prohibited items in X-ray images.At the same time,a series of data augmentation methods such as image rotation were used to expand the sample size for a small number of category samples.Experiments were conducted on a self-building X-ray security inspection image dataset,and the results showed that the improved algorithm enhanced detection accuracy by 6％compared to the original YOLOv8n model,increased detection speed by 15.7％compared to the original YOLOv8n model,and reduced the missed detection rate of a small number of categories.关键词
YOLOv8n/ECA注意力/深度学习/X线图像/违禁品检查Key words
YOLOv8n/ECA attention/deep learning/X-ray images/prohibited goods inspection分类
力学引用本文复制引用
毛玮杨,杨军,刘栩栋,梁道正..基于改进YOLOv8的X线安检图像违禁品检测方法[J].四川师范大学学报（自然科学版）,2025,48(2):253-260,8.基金项目
国家自然科学基金(62006165)和四川省自然科学基金(2022NSFSC0552) （62006165）
