모바일환경에서 위조서명에 강건한 딥러닝 기반의 핑거서명검증 연구
Mobile Finger Signature Verification Robust to Skilled Forgery
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
본 논문에서는 스마트폰에서 손가락으로 서명하는 동적서명에서 위조서명에 강건한 검증 방법을 제안한다. 본 논문에서는 위조서명을 효과적으로 구분할 수 있도록 재생산 신경망의 일종인 1 class Auto-Encoder 모델을 사용한다. 핑거서명에서는 지원되지 않는 펜 압력 등 기존의 특징 정보 대신 대부분의 스마트폰에서 지원하는 가속도센서를 추가로 활용하여 서명이 이루어지고 있는 동안 스마트폰의 동적인 움직임의 특징정보를 추출한다. 서명 데이터는 리샘플링을 통해 길이를 맞추고, 일정한 크기로 정규화하여 사용한다. 제안 방법의 성능을 평가하기 위해 테스트셋을 구축하여단일세션검증, 시간차 검증, 위조서명 검증의 3가지 실험을 실시하였다. 실험결과 위조서명 구분에 있어서 제안방법은기존 방법보다 EER이 최대 6.9% 더 낮았다. 또한, 서명의 모양과 속도만 사용한 기존의 방식보다 가속도센서를 추가한 방식이 1.5% 나은 성능을 보였고, 최고 3.5%의 에러율을 얻었다.
Abstract
In this paper, we provide an authentication technology for verifying dynamic signature made by finger on smart phone. In the proposed method, we are using the Auto-Encoder-based 1 class model in order to effectively distinguish skilled forgery signature. In addition to the basic dynamic signature characteristic information such as appearance and velocity of a signature, we use accelerometer value supported by most of the smartphone. Signed data is re-sampled to give the same length and is normalized to a constant size. We built a test set for evaluation and conducted experiment in three ways. As results of the experiment, the proposed acceleration sensor value and 1 class model shows 6.9% less EER than previous method.
참고문헌 (29)
- S.S. Arora, "3D fingerprint phantoms", Proc. of 22nd Int. Conf. on Pattern Recognition, pp.684~689 (2014)
- H. Malik, "Audio Forensics from Acoustic Reverberation", Proc. IEEE Int’l Conf. Acoustics, Speech, Signal Processing, pp.1710~1713 (2010)
- T. Fladsrud, "Face recognition in a border control environment: Non-zero effort attacks effect on false acceptance rate", Master, pp.2005
- D. Kim, "Gait recognition using active shape model and motion prediction", Computer Vision IET, 4(1), pp.25~36 (2010)
- M. C. Thomas, "A comprehensive review on vision based hand gesture recognition technology", International Journal of Research in Advent Technology, 2(1), pp.303~310 (2014)
- R. P. Krish, "Dynamic Signature Verification on Smart Phones", In Communications in Computer and Information Science, 365, pp.213~222 (2013)
- M. Martinez-Diaz, "Towards mobile authentication using dynamic signature verification : useful features and performance evaluation", Proceedings of the International Conference on Pattern Recognition, ICPR, pp.1~5 (2008)
- N. Sae-Bae, "Online signature verification on mobile devices", IEEE Trans. Inf. Forensics Security, 9(6), pp.933~947 (2014)
- N. Paudel, "Handwritten Signature Verification for Mobile Phones", International Conference on Information Systems Security and Privacy(ICISSP), pp.46~52 (2016)
- M. A. Ferrer, "Offline geometric parameters for automatic signature verification using fixed-point arithmetic", IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(6), pp.993~997 (2005)
- R. Kumar, "Writer-independent off-line signature verification using surroundedness feature", Pattern Recognition Letters, 33(3), pp.301~308 (2012)
- G. Dimauro, "Recent Advancements in Automatic Signature Verification", Int’l Workshop on Frontiers in Handwriting Recognition(IWFHR), pp.179~184 (2004)
- N. Li, "Online Signature Verification Based on Biometric Features", International Conference on System Sciences, pp.5527~5534 (2016)
- A. Fischer, "Robust score normalization for DTW-based on-line signature verification", International Conference on document analysis and recognition, pp.241~245 (2015)
- W.S. Wijesoma, "On-line signature verification using a computational intelligence approach", Lecture Notes in Computer Science, 2206, pp.699~711 (2001), Springer-Verlag
- S.Y. Ryu, "A Robust On-line Signature Verification System", International Journal of Fuzzy Logic and Intelligent Systems, 3(1), pp.27~31 (2003)
- C. Gruber, "Online Signature Verification With Support Vector Machines Based on LCSS Kernel Functions", IEEE Transactions on Systems Browse Journals & Magazines, 40(4), pp.1088~1100 (2010)
- V. Irnmanesh, "Online Signature Verification Using Neural Network and Pearson Correlation Features", IEEE Conference on Open Systems (ICOS), pp.18~21 (2014)
- A. Makhzani, "Winner-take-all autoencoders", Neural Information Processing Systems(NIPS), 2773~2781 (2015)
- M. Fayyza, "Online Signature Verification Based on Feature Representation", IEEE Artificial Intelligence and signal Processing, pp.211~216 (2015)
- D.I. Chae, "Hidden Singer Contest:Auto-encoder based singer Identification", Joint Conference on communications and Information(JCCI), pp.629~632 (2016)
- P.O. Kristensson, "Continuous recognition of one-handed and two-handed gestures using 3D full-body motion tracking sensors", Proc. of ACM Int'l. Conf. on Intelligent User Interfaces, pp.89~92 (2012)
- P.O. Kristensson, "Continuous recognition and visualization of pen strokes and touch-screen gestures", Proc. of Euro graphics Symposium on Sketch-Based Interfaces and Modeling, pp.95~102 (2011)
- R. Reed, "Neural smithing supervised learning in feedforward artificial neural networks" (1999), MIT press
- A. Krizhevsky, "Using very deep autoencoders for content-based image retrieval", Proceedings of the European Symposium of Artifical Neural Networks, pp.489~494 (2011)
- A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", In Neural Information Processiong Systems, ~ (2012)
- Y. N. Dauphi, "Equilibrated adaptive learning rates for non-convex optimization", arXiv preprint arXiv : 2502. 04390, ~ (2015)