Concealed objects detection based on FWT in active millimeter-wave images

Kun Du; Lu Zhang; Wei Chen; Guolong Wan; Ruoran Fu

doi:10.1117/12.2265504

23 January 2017 Concealed objects detection based on FWT in active millimeter-wave images

Kun Du, Lu Zhang, Wei Chen, Guolong Wan, Ruoran Fu

Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103221O (2017) https://doi.org/10.1117/12.2265504
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China

Abstract

Active millimeter-wave (MMW) near-filed human imaging is a means for concealed objects detection. A method of concealed objects detection based on fast wavelet transforms (FWT) in the usage of active MMW images is presented as a result of image characteristics, which includes high resolution, characteristics varying in different parts of the human, imaging influenced among human, concealed objects and other objects, and different textures of concealed objects. Images segmentation utilizing results of edge detection based on FWT is conducted and preliminary segmentation results can be obtained. Some kinds of concealed objects according to comparing gray value of concealed objects to human average gray value can be detected in this paper. The experiments of concealed objects on images of actual acquisition are conducted with a result of accurate rate 80.92% and false alarm rate 11.78%, illustrating the effectiveness of the method proposed in this paper.

Citation Download Citation

Kun Du, Lu Zhang, Wei Chen, Guolong Wan, and Ruoran Fu "Concealed objects detection based on FWT in active millimeter-wave images", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103221O (23 January 2017); https://doi.org/10.1117/12.2265504

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available