TDARS, a fusion based AR system for machine readable travel documents

Authors:
Yu Wu;Ling Xue;Chao Li;Zhang Xiong
Affiliations:
School of Computer Science and Technology, Beihang University, Beijing, P.R. China;School of Computer Science and Technology, Beihang University, Beijing, P.R. China;School of Computer Science and Technology, Beihang University, Beijing, P.R. China;School of Computer Science and Technology, Beihang University, Beijing, P.R. China
Venue:
Proceedings of the 2007 conference on Human interface: Part II
Year:
2007

Citing 4
Cited 0

Fuzzy sets and fuzzy logic: theory and applications

Fuzzy sets and fuzzy logic: theory and applications
A Generic System for Form Dropout

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
An embedded HMM-based approach for face detection and recognition

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06

Quantified Score

Hi-index	0.00

Visualization

Abstract

A fuzzy set-based AR (Automatic Recognition) system named TDARS for machine readable travel documents (MRTDs) is designed and implemented for speeding up customs clearance. The system consists of three parts: text feature extraction, facial feature extraction and identity matching. Text feature extraction takes charge of locating machine readable zone (MRZ) and extracts text features automatically. Facial feature extraction focuses on locating the front face photo (FFP) in the MRTD and extracting the facial features of the MRTD possessor. Identity matching compares text and facial features with feature data in the Terrorist Database (TDB) respectively and fuses the matching results of text and facial features in the decision-making level using a fuzzy set based algorithm. Experimental results show that both the correct acceptance and refusal rates of the TDARS are over 90%, which evidently exceed those of the existing recognition systems that extract text features solely.