On Using Entropy for Enhancing Handwriting Preprocessing

Handwriting is an important modality for Human-Computer Interaction. For medical professionals, handwriting is (still) the preferred natural method of documentation. Handwriting recognition has long been a primary research area in Computer Science. With the tremendous ubiquity of smartphones, along with the renaissance of the stylus, handwriting recognition has become a new impetus. However, recognition rates are still not 100% perfect, and researchers still are constantly improving handwriting algorithms. In this paper we evaluate the performance of entropy based slant- and skew-correction, and compare the results to other methods. We selected 3700 words of 23 writers out of the Unipen-ICROW-03 benchmark set, which we annotated with their associated error angles by hand. Our results show that the entropy-based slant correction method outperforms a window based approach with an average precision of ±6.02° for the entropy-based method, compared with the ±7.85° for the alternative. On the other hand, the entropy-based skew correction yields a lower average precision of ±2:86°, compared with the average precision of ±2.13° for the alternative LSM based approach.

[1]  Daniel Vogel,et al.  Shift: a technique for operating pen-based interfaces using touch , 2007, CHI.

[2]  Patrick Baudisch,et al.  Understanding touch , 2011, CHI.

[3]  Réjean Plamondon,et al.  Normalizing and restoring on-line handwriting , 1993, Pattern Recognit..

[4]  Andreas Holzinger,et al.  Mobile computer Web-application design in medicine: some research based guidelines , 2007, Universal Access in the Information Society.

[5]  Andreas Holzinger,et al.  Typical Problems with Developing Mobile Applications for Health Care - Some Lessons Learned from Developing User-centered Mobile Applications in a Hospital Environment , 2008, ICE-B.

[6]  Ching Y. Suen,et al.  The State of the Art in Online Handwriting Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Andreas Holzinger,et al.  Preferences of handwriting recognition on mobile information systems in medicine: Improving handwriting algorithm on the basis of real-life usability research , 2010, 2010 International Conference on e-Business (ICE-B).

[8]  Isabelle Guyon,et al.  UNIPEN project of on-line data exchange and recognizer benchmarks , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[9]  Sargur N. Srihari,et al.  Off-Line Cursive Script Word Recognition , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Marcos Faúndez-Zanuy,et al.  An Information Analysis of In-Air and On-Surface Trajectories in Online Handwriting , 2011, Cognitive Computation.

[11]  Thomas G. Holzman.  Computer-human interface solutions for emergency medical care , 1999, INTR.

[12]  Andreas Kosmala.  HMM-basierte Online Handschrifterkennung: ein integrierter Ansatz zur Text- und Formelerkennung , 2000 .

[13]  Andreas Holzinger,et al.  User-Centered Interface Design for Disabled and Elderly People: First Experiences with Designing a Patient Communication System (PACOSY) , 2002, ICCHP.

[14]  Ching Y. Suen,et al.  Nonlinear shape restoration by transformation models , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[15]  Seong-Whan Lee,et al.  Automatic quality measurement of gray-scale handwriting based on extended average entropy , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  James R. Lewis.  Input Rates and User Preference for Three Small-Screen Input Methods: Standard Keyboard, Predictive Keyboard, and Handwriting , 1999 .

[17]  Ching Y. Suen,et al.  Automatic reading of cursive scripts using a reading model and perceptual concepts , 1998, International Journal on Document Analysis and Recognition.

[18]  Andreas Holzinger,et al.  Handwriting recognition on mobile devices: State of the art technology, usability and business analysis , 2011, Proceedings of the International Conference on e-Business.

[19]  V. Anantharaman,et al.  Hospital and emergency ambulance link: using IT to enhance emergency pre-hospital care , 2001, Int. J. Medical Informatics.

[20]  Ashish Chaturvedi,et al.  Machine Recognition of Hand Written Characters using Neural Networks , 2011, ArXiv.

[21]  Daniel K Sokol,et al.  Poor Handwriting Remains a Significant Problem in Medicine , 2006 .

[22]  Yuan Yan Tang,et al.  Entropy-Reduced Transformation Approach to Pattern Recognition of Complex Data Set , 1988, MVA.

[23]  Andreas Holzinger,et al.  Design and development of a mobile computer application to reengineer workflows in the hospital and the methodology to evaluate its effectiveness , 2011, J. Biomed. Informatics.

[24]  Gerhard Rigoll,et al.  Comparing normalization and adaptation techniques for online handwriting recognition , 2002, Object recognition supported by user interaction for service robots.

[25]  Richard F. Lyon,et al.  Combining Neural Networks and Context-Driven Search for On-Line, Printed Handwriting Recognition in the Newton , 1996, Neural Networks: Tricks of the Trade.

[26]  Murray Eden,et al.  Handwriting and pattern recognition , 1962, IRE Trans. Inf. Theory.

[27]  Sung Yang Bang,et al.  A variation measure for handwritten character image data using entropy difference , 1997, Pattern Recognit..

[28]  M Balter.  Paintings in Italian Cave May Be Oldest Yet , 2000, Science.

[29]  Yan Gao,et al.  Handwriting Character Recognition as a Service: A New Handwriting Recognition System Based on Cloud Computing , 2011, 2011 International Conference on Document Analysis and Recognition.

[30]  Patrick Baudisch,et al.  Back-of-device interaction allows creating very small touch devices , 2009, CHI.

[31]  Luca Chittaro,et al.  Mobile Devices in Emergency Medical Services: User Evaluation of a PDA-Based Interface for Ambulance Run Reporting , 2007, Mobile Response.

[32]  Michael Rohs,et al.  BYOD: bring your own device , 2004 .

[33]  Luca Chittaro,et al.  Hci for emergencies , 2008, CHI Extended Abstracts.

[34]  Martina Ziefle,et al.  Investigating paper vs. screen in real-life hospital workflows: Performance contradicts perceived superiority of paper in the user experience , 2011, Int. J. Hum. Comput. Stud..

[35]  Christian Lovis,et al.  Research Paper: Handheld vs. Laptop Computers for Electronic Data Collection in Clinical Research: A Crossover Randomized Trial , 2009, J. Am. Medical Informatics Assoc..

[36]  Seong-Whan Lee,et al.  Advances in Handwriting Recognition , 1999, Series in Machine Perception and Artificial Intelligence.

[37]  Patrick Baudisch,et al.  Lucid touch: a see-through mobile device , 2007, UIST.

[38]  D. Baumgart.  Personal digital assistants in health care: experienced clinicians in the palm of your hand? , 2005, The Lancet.

[39]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[40]  M. Tahar Kechadi,et al.  Preprocessing Techniques for Online Handwriting Recognition , 2009, Intelligent Text Categorization and Clustering.

[41]  Gerhard Rigoll,et al.  Novel script line identification method for script normalization and feature extraction in on-line handwritten whiteboard note recognition , 2009, Pattern Recognit..

[42]  Nikos Fakotakis,et al.  New algorithms for skewing correction and slant removal on word-level [OCR] , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[43]  Lyel M. Hess.  The History and Development of Handwriting From Prehistoric Times to 1925 , 1937 .

[44]  Andreas Holzinger,et al.  An investigation of finger versus stylus input in medical scenarios , 2008, ITI 2008 - 30th International Conference on Information Technology Interfaces.

[45]  Vom Fachbereich Elektrotechnik.  HMM-basierte Online Handschrifterkennung — ein integrierter Ansatz zur Text- und Formelerkennung , 2000 .

[46]  Richard F. Lyon,et al.  Combining Neural Networks and Context-Driven Search for Online, Printed Handwriting Recognition in the NEWTON , 1998, AI Mag..

[47]  Andreas Holzinger,et al.  Finger Instead of Mouse: Touch Screens as a Means of Enhancing Universal Access , 2002, User Interfaces for All.

[48]  Seiichi Uchida,et al.  Nonuniform Slant Correction for Handwritten Word Recognition , 2004, IEICE Trans. Inf. Syst..

[49]  Ghazali Sulong,et al.  Simple and effective techniques for core-region detection and slant correction in offline script recognition , 2009, 2009 IEEE International Conference on Signal and Image Processing Applications.

[50]  Andreas Holzinger,et al.  Biometrical Signatures in Practice: A challenge for improving Human-Computer Interaction in Clinical Workflows , 2006, Mensch & Computer.