Can I read Applsci 11 10261 on EtoBox?
Applsci 11 10261 by yeatlidiya65 is a document available to read on EtoBox.
What is Applsci 11 10261 about?
This paper explores the use of pixel-level analysis to enhance threat detection in X-ray security images, focusing on the integration of segmentation deep learning models into the detection pipeline. By employing a Faster R-CNN model for threat localization and a DeepLabV3+ model for pixel classification, the authors achieved significant improvements in detection accuracy, with mean average precisions of up to 94.88%. The study highlights the importance of addressing class imbalance in X-ray datasets and in
- Author
- yeatlidiya65
- Language
- EN