Millimeter-Wave Image Target Recognition Based on the Combination of Shape Features

Dai, Ling1; Hu, Hong1; Chen, Yifan2; Zhou, Min2; IEEE

10.1109/ICInfA.2016.7832097

2016

2016 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA)

1732-1736

Ningbo, China

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Shape features are widely used in image target recognition due to their useful property of translation, rotation and scaling invariance. In this paper, low order Hu moments and other four shape features are combined together to classify different kinds of knives and guns with the support vector machine in the application of millimeter wave security imaging. Experimental results show that the combined features have better invariance and differences than other invariant moments.

Feature extraction Combined features Invariants Target recognition

通讯

英语

CPCI-S ; EI

Automation & Control Systems ; Computer Science

Automation & Control Systems ; Computer Science, Information Systems

WOS:000405519500310

20171203484859

Feature extraction ; Partial discharges

Electricity: Basic Concepts and Phenomena:701.1 ; Electromagnetic Waves:711

Web of Science

1.Harbin Inst Technol, Shenzhen Grad Sch, Sch Mech Engn & Automat, Shenzhen 518055, Peoples R China
2.South Univ Sci & Technol China, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China

Dai, Ling,Hu, Hong,Chen, Yifan,et al. Millimeter-Wave Image Target Recognition Based on the Combination of Shape Features[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2016:1732-1736.