DocumentCode :
3669428
Title :
Automatic detection of concealed pistols using passive millimeter wave imaging
Author :
Zelong Xiao;Xuan Lu;Jiangjiang Yan;Li Wu;Luyao Ren
Author_Institution :
School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China
fYear :
2015
Firstpage :
1
Lastpage :
4
Abstract :
A method is proposed for automatic detection of the concealed pistols detected by passive millimeter in security applications. In this paper, we extend four half-surrounded Haar-like features and use integral image to rapidly calculate the rectangle features. Then we obtain a multi-layer classifier cascaded by several strong classifiers using AdaBoost algorithm to detect the contraband. Various passive millimeter images from both published literatures and our own measurements are used for training and testing. The experimental results show that the metallic pistols in different sizes, shapes, and angles can be accurately detected, so this method is useful for automatic detection of pistols.
Keywords :
"Feature extraction","Imaging","Classification algorithms","Millimeter wave technology","Training","Image recognition","Object detection"
Publisher :
ieee
Conference_Titel :
Imaging Systems and Techniques (IST), 2015 IEEE International Conference on
Type :
conf
DOI :
10.1109/IST.2015.7294538
Filename :
7294538
Link To Document :
بازگشت