Reduced Dynamic Time Warping for Handwriting Recognition Based on Multidimensional Time Series of a Novel Pen Device

Autor: Bashir, Muzaffar, Kempf, Jürgen
Jazyk: angličtina
Rok vydání: 2008
Předmět:
DOI: 10.5281/zenodo.1081501
Popis: The purpose of this paper is to present a Dynamic Time Warping technique which reduces significantly the data processing time and memory size of multi-dimensional time series sampled by the biometric smart pen device BiSP. The acquisition device is a novel ballpoint pen equipped with a diversity of sensors for monitoring the kinematics and dynamics of handwriting movement. The DTW algorithm has been applied for time series analysis of five different sensor channels providing pressure, acceleration and tilt data of the pen generated during handwriting on a paper pad. But the standard DTW has processing time and memory space problems which limit its practical use for online handwriting recognition. To face with this problem the DTW has been applied to the sum of the five sensor signals after an adequate down-sampling of the data. Preliminary results have shown that processing time and memory size could significantly be reduced without deterioration of performance in single character and word recognition. Further excellent accuracy in recognition was achieved which is mainly due to the reduced dynamic time warping RDTW technique and a novel pen device BiSP.
{"references":["http://www.bisp-regensburg.de","C. Gruber, C. Hook, J. Kempf, G. Scharfenberg, B. Sick, \" A Flexible\nArchitecture for Online Signature Verification Based on a Novel\nBiometric Pen\" In Proceedings of the 2006 IEEE Mountain Workshop\non Adaptive and Learning Systems (SMCals/06)\"; pp. 110-115; Logan,\n2006.","T. Gruber, C. Gruber, B. Sick, \" Online Signature Verification With new\nTime Series Kernels for Support Vector Machines\" D. Zhang, A. K.\nJain (Eds.) Advances in Biometrics: International Conference ICB 2006;\nLecture Notes in Computer Science 3832, Springer Verlag, Berlin,\nHeidelberg, New York; pp. 500-508; Hong Kong, 2006","Hook C., Kempf J., Scharfenberg, G.\"New Pen Device for Biometrical\n3D Pressure Analysis of Handwritten Characters, Words and\nSignatures.\" Proceedings ACM Multimedia Berkeley, USA (2003) 38-\n44","Hook C., Kempf J., Scharfenberg G, \"A Novel Digitizing Pen for the\nAnalysis of Pen Pressure and Inclination in handwriting Biometrics\",\nBiometric Authentication Workshop, Prague 2004, Lecture Notice in\nComputer Science. Springer 2004.","┼áoule M., Kempf J. \"Handwritten Text Analysis through Sound. A New\nDevice for Handwriting Analysis\", In Proceedings IWSSIP, Prague,\n(2003) 254-257","┼áoule, M, \"Person Authentification Using Acoustic Handwritten Text\",\nPh.D. thesis, Pilsen (2007), Czech Republic.","M. Dose, C. Gruber, A. Grunz, C. Hook, J. Kempf, G. Scharfenberg, B.\nSick, \"Towards an Automated Analysis of Neuroleptics- Impact on\nHuman Hand Motor Skills\", In Proceedings of the 2007 IEEE\nSymposium on Computational Intelligence in Bioinformatics and\nComputational Biology (CIBCB 2007)\"; pp. 494-501, Honolulu, 2007","A. Ünlü, R. Brause, K. Krakow,\" Handwriting Analysis for Diagnosis\nand Prognosis of Parkinson-s Disease\", Proc.Int. Symp. Biological and\nMedical Data analysis, LNCS Vol. 4345,Springer Heidelberg\n2006,pp.441-450\n[10] TakitaT., Hangai S., Kempf J, Hook C., Scharfenberg G., \"An\nIdentification of Japanese Numerical Characters on a Biometrical Smart\nPen System\", In Automatic Identification Advanced Technologies, 2007\nIEEE Workshop, June 2007.\n[11] Tapperet C., Suen C., Wakahara T, \"The State of the Art in On-line\nHandwriting Recognition\", IEEE Trans. Pattern Analysis and Machine\nIntelligence, Vol.12, No.8, 1990, pp.787-808.\n[12] R. Niels, L. Vuurpijl, \"Dynamic Time Warping Applied to Tamil\nCharacter Recognition\". Proceedings of the 8th International Conference\non Document Analysis and Recognition, 2005.\n[13] Marcos Faundez Zanuy, \"On-line signature recognition based on VQDTW\",\nELSEVIER, June, 2006.\n[14] Kruskall, J.B., Liberman,M., \"The Symmetric Time Warping Algorithm:\nFrom continuous to discrete\". In time Warps, String Edits and\nMacromolecules: The Theory and Practice of Sequence Comparison,\npp.125-161,, Addison -Wesley (1983)\n[15] Eamonn J. Keogh, Michael J. Pazzani, \"Derivative Dynamic Time\nWarping\" In Proc. Of the 1st SIAM Int.Conf. on Data Mining (SDM-\n2001).\n[16] V. Vuori, J. Laaksonen, E. Oja, J. Kangas, \"Speeding up On-line\nRecognition of Handwritten Characters by Pruning the Prototype Set\" In\nProc.Of (ICDAR-01), pp.501-505.\n[17] Salvador S., Chan P.: \"FastDTW: Toward Accurate Dynamic Time\nWarping in Linear Time and Space\", Intelligent Data Analysis, 2007.\n[18] H. Sakoe, S. Chiba, \"Dynamic programming algorithm optimization for\nspoken word recognition\". IEEE Transaction on Acoustics, Speech and\nSignal Processing, Vol 26, NO1, pp. 43-49. February 1978.\n[19] http://www.bromba.com/faq/biofaqe.htm#ROC\n[20] www.mathworks.com"]}
Databáze: OpenAIRE
Externí odkaz: