[好文] 50 Years of Biometric Research: Accomplishments, Challenges, and Opportunit

韩琥计算所

密歇根州立大学Anil K. Jain 教授亲自写的对生物特征识别过去五十年前所取得的研究进展总结，挑战性问题以及未来发展的展望。
Anil K. Jain, Karthik Nandakumar, Arun Ross, 50 Years of Biometric Research: Accomplishments, Challenges, and Opportunities, Pattern Recognition Letters, Available online 12 January 2016, ISSN 0167-8655,
论文下载：
JainNandakumarRoss_50Years_PRL2016.pdf (10.83 MB, 下载次数: 5582)

2016-1-17 18:53 上传

点击文件名下载附件

Biometric recognition refers to the automated recognition of individuals based on their biological andbehavioral characteristics such as fingerprint, face, iris, and voice. The first scientific paper on automatedfingerprint matching was published by Mitchell Trauring in the journal Nature in 1963. Thefirst objective of this paper is to document the significant progress that has been achieved in the fieldof biometric recognition in the past 50 years since Trauring’s landmark paper. This progress hasenabled current state-of-the-art biometric systems to accurately recognize individuals based on biometrictrait(s) acquired under controlled environmental conditions from cooperative users. Despitethis progress, a number of challenging issues continue to inhibit the full potential of biometrics toautomatically recognize humans. The second objective of this paper is to enlist such challenges, analyzethe solutions proposed to overcome them, and highlight the research opportunities in this field.One of the foremost challenges is the design of robust algorithms for representing and matching biometricsamples obtained from uncooperative subjects under unconstrained environmental conditions(e.g., recognizing faces in a crowd). In addition, fundamental questions such as the distinctivenessand persistence of biometric traits need greater attention. Problems related to the security of biometricdata and robustness of the biometric system against spoofing and obfuscation attacks, also remainunsolved. Finally, larger system-level issues like usability, user privacy concerns, integration withthe end application, and return on investment have not been adequately addressed. Unlocking thefull potential of biometrics through inter-disciplinary research in the above areas will not only lead towidespread adoption of this promising technology, but will also result in wider user acceptance andsocietal impact.