Intelligent detection method for forbidden articles based on terahertz characteristics

The invention belongs to the technical field of spectral analysis, and provides a terahertz feature-based intelligent detection method for forbidden articles, which comprises the following steps of: acquiring a certain frame of image in a shot terahertz image, preprocessing the image, and preliminar...

Full description

Saved in:
Bibliographic Details
Main Authors HU QIUSHENG, YAO BINBIN, HU JINWEN, PAN RONG, TIAN WEI
Format Patent
LanguageChinese
English
Published 28.11.2023
Subjects
CALCULATING
COMPUTING
COUNTING
DETECTING MASSES OR OBJECTS
GEOPHYSICS
GRAVITATIONAL MEASUREMENTS
MEASURING
PHYSICS
TESTING
Online AccessGet full text

Cover

More Information
Summary:The invention belongs to the technical field of spectral analysis, and provides a terahertz feature-based intelligent detection method for forbidden articles, which comprises the following steps of: acquiring a certain frame of image in a shot terahertz image, preprocessing the image, and preliminarily eliminating noise; the preprocessed image is calculated, noise caused by vibration is accurately distinguished, and the image is denoised according to a judgment result; and identifying whether the target object is a forbidden object or not for the de-noised image by adopting a neural network model, and completing intelligent detection of the forbidden object. Through a special denoising means provided by the method, vibration ghost noise generated by vibration is eliminated, the image quality of the terahertz feature map is greatly improved, the forbidden article detection method based on terahertz features has higher environmental robustness, and a final intelligent detection result can be more accurate. 本申请属
Bibliography:Application Number: CN202311399219