Tapas Kanungo's Optical Character Recognition (OCR) Page

• What is Optical Character Recognition?
• Degradation Models
• Degradtion Model Validation
• Degradtion Model Estimation
• Document Restoration
• Layout Recognition
• Multilingual OCR
• Information/Entity Extraction
• Performance Evaluation and Groundtruthing Tools
• Digital Libraries and Web
• Surveys
• Edited Volumes
• Software
• Multilingual OCR Workshop
• OCR Course

What is Optical Character Recognition?

• Optical Character Recognition
  McGraw Hill 2007 Year Book, McGraw Hill, 2007
  by T. Kanungo
  

  Degradation Models

• Nonlinear Local and Global Document Degradation Models
  Int. Journal of Imaging Systems and Technology Vol. 5, no. 4, John Wiley, pp. 220-30, Fall 1994
  by T. Kanungo, R. M. Haralick, and I. Phillips
  Download pdf
  
• Global and Local Document Degradation Models
  Proc. of Int. Conf. on Document Analysis and Recognition IEEE Press, Tsukuba, Japan, pp. 730-734, October, 20-22, 1993
  by T. Kanungo, R. M. Haralick, I. Phillips
  Download ps pdf
  

  Degradation Model Validation

• Statistical, Nonparametric Methodology for Document Degradation Model Validation
  IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1209-1223, November 2000
  by T. Kanungo, R. M. Haralick, H. S. Baird, W. Stuezle, and D. Madigan
  Download pdf
  
• Document Degradation Models: Parameter Estimation and Model Validation
  Proc. of IAPR Workshop on Machine Vision and Applications Kawasaki, Japan, 1994, pp. 552-7
  by T. Kanungo, R. M. Haralick, H. S. Baird, W. Stutzle, and D. Madigan
  
  
• Estimation and Validation of Document Degradation Models
  Proc. of Symposium on Document Analysis and Information Retrieval Las Vegas, NV, 1995, pp. 217-228
  by T. Kanungo, H. S. Baird and R. M. Haralick
  
  
• Power Functions and their Use in Selecting Distance Functions for Document Degradation Model Validation
  Proc. of Int. Conf. on Document Analysis and Recognition, Montreal, Canada, 1995, pp. 734-9, Vol. 2,
  by T. Kanungo, R. M. Haralick, and H. S. Baird
  Download pdf
  

  Degradation Model Parameter Estimation

• Estimating Degradation Model Parameters using Neighborhood Pattern Distributions: An Optimization Approach
  IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 4, pp. 520-524, 2004.
  by T. Kanungo and Q. Zheng
  Download pdf
  
• Estimation of Morphological Degradation Model Parameters
  Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Salt Lake City, UT, pp. 1961-1964, May 2001
  by T. Kanungo and Q. Zheng
  Download pdf
  
• Estimation of Morphological Degradation Parameters
  Proc. SPIE Conference on Nonlinear Imaging, San Jose, CA, pp. 86-95, vol. 2424, February 6–9, 1995
  by T. Kanungo and R. M. Haralick
  
  

  Document Restoration

• Model-based Restoration of Degraded Documents
  Proc. of IEEE Int. Conf. on Image Processing, Greece, pp. 193-196, 2001.
  by Q. Zheng and T. Kanungo
  Download pdf
  

  Multilingual OCR

• The Bible and Multilingual Optical Character Recognition
  Communications of the ACM, vol. 48, no. 6, pp. 124-130, 2005.
  by T. Kanungo, P. Resnik, S. Mao, D. Kim and Q. Zheng
  Download pdf
  
• The Bible, Truth, and Multilingual OCR Evaluation
  Proc. of SPIE Conf. on Document Recognition and Retrieval (VI), vol. 3651, San Jose, CA, January 27-28, 1999
  by T. Kanungo and P. Resnik
  Download pdf
  
• Automatic language identification system for multilingual optical character recognition
  US patent US6047251, Caere Corporation, 4 April, 2000.
  by L. K. Pon, T. Kanungo, J. Yang, K. C. Choy and M. R. Bokser
  Download pdf
  
• Automatic language identification system for multilingual optical character recognition
  European patent, EP1016033B1, Scansoft, Inc., 18 June 2003.
  by L. K. Pon, T. Kanungo, J. Yang, K. C. Choy and M. R. Bokser
  Download pdf
  
• Performance Evaluation of Two Arabic OCR Products
  Proc. of AIPR Workshop on Advances in Computer Assisted Recognition, SPIE vol. 3584 Washington DC, October 14-16, 1998.
  by T. Kanungo and G. E. Marton and O. Bulbul
  Download pdf
  
• OmniPage vs. Sakhr: Paired Model Evaluation of Two Arabic OCR Products
  Proc. of SPIE Conf. on Document Recognition and Retrieval (VI), vol. 3651 San Jose, CA, January 27-28, 1999
  by T. Kanungo, G. A. Marton and O. Bulbul
  Download pdf
  

  Layout Recognition

• Stochastic Language Models for Style-Directed Physical Layout Analysis of Documents
  IEEE Transactions on Image Processing, vol. 12, no. 5, pp. 583-596, 2003.
  by T. Kanungo and S. Mao
  Download pdf
  
• Stochastic Language Models for Analyzing Physical Layout of Documents
  Proc. of SPIE Conf. on Document Recognition and Retrieval, San Jose, CA, pp. 28-36, January 2002.
  by T. Kanungo and S. Mao
  
  
• Stochastic Language Models for Automatic Acquisition of Lexicons from Printed Bilingual Dictionaries
  Proc. of Document Layout Interpretation and its Applications, Seattle, WA, Sept. 9, 2001.
  by S. Mao and T. Kanungo
  
  
• Empirical Performance Evaluation Methodology and its Application to Page Segmentation Algorithms
  IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 242-256, March 2001
  by S. Mao and T. Kanungo
  Download pdf
  
• Automatic Training of Page Segmentation Algorithms: An Optimization Approach
  Proc. of IAPR Int. Conf. on Pattern Recognition Barcelona, Spain, September 3-8, 2000
  by S. Mao and T. Kanungo
  Download pdf
  
• Document Structure Analysis: A Survey
  Proc. of SPIE Conf. on Document Recognition and Retrieval, Santa Clara, CA, pp. 197-207, January 2003.
  by S. Mao, A. Rosenfeld, and T. Kanungo
  Download pdf
  
• Empirical Performance Evaluation of Page Segmentation Algorithms
  Proc. of SPIE Conf. on Document Recognition and Retrieval (VII) San Jose, CA, January 26-27, 2000
  by Song Mao and Tapas Kanungo
  Download pdf
  

  Information/Entity Extraction

• Baseline Experiments for OCR-Based Arabic Named-Entity Extraction
  Proc. of IAPR Int. Workshop on Document Analysis Systems, Rio de Janeiro, Brazil, December 2000
  T. Kanungo and O. Bulbul
  Download pdf
  
• Character Recognition Using Mathematical Morphology
  Proc. of USPS Fourth Advanced Technology Conference Washington, D.C., pp. 973-986, Nov. 5-7, 1990
  by T. Kanungo and R. M. Haralick
  Download ps
  

  Performance Evaluation and Groundtruthing Tools

• The Architecture of TRUEVIZ: A GroundTRUth/Metadata Editing and VISualiZing Toolkit
  Pattern Recognition, vol. 36, no. 3, pp. 811-825, 2003.
  by C. H. Lee and T. Kanungo
  Download pdf
  
• TRUEVIZ: A groundTRUth/metadata Editing and VisualiZing Toolkit for OCR
  Proc. of SPIE Conf. on Document Recognition and Retrieval, San Jose, CA, January 2001.
  by T. Kanungo, C. Lee, J. Czorapinski and I. Bella
  
  
• An Automatic Closed-Loop Methodology for Generating Character Groundtruth for Scanned Documents
  IEEE Transactions on Pattern Analysis and Machine Intelligence vol. 21, no. 2, pp. 179-183, February, 1999
  by T. Kanungo and R. M. Haralick
  Download pdf
  
• Automatic Generation of Character Groundtruth for Scanned Documents: A Closed-Loop Approach
  Proc. of Int. Conf. on Pattern Recognition, Vienna, Austria, 1996,
  by T. Kanungo, R. M. Haralick
  Download ps
  
• Attributed Point Matching for Automatic Groundtruth Registration
  Int. Journal on Document Analysis and Recognition, vol. 5, no. 1, pp. 47-66, 2002.
  by D. Kim and T. Kanungo
  
  
• A Point Matching Algorithm for Automatic Generation of Groundtruth for Document Images
  Proc. of IAPR Int. Workshop on Document Analysis Systems, Rio de Janeiro, Brazil, December 2000.
  D. W. Kim and T. Kanungo
  Download pdf
  
• Software Architecture of PSET: A Page Segmentation Evaluation Toolkit
  Int. Journal on Document Analysis and Recognition, vol. 4, no. 3, pp. 205-217, 2002.
  by S. Mao and T. Kanungo
  Download pdf
  
• PSET: A Page Segmentation Evaluation Toolkit
  Proc. of IAPR Int. Workshop on Document Analysis Systems, Rio de Janeiro, Brazil, December 2000.
  S. Mao and T. Kanungo
  Download pdf
  

  Digital Libraries, Web

• Full-Text Access to Historical Newspapers
  CS-TR-4014, University of Maryland, College Park, MD, April 1999.
  by T. Kanungo and R. B. Allen
  Download pdf
  
• What Fraction of Images on the Web Contain Text?
  Proc. of Int. Workshop on Web Document Analysis, Seattle, WA, Sept. 8, 2001.
  by T. Kanungo, C. H. Lee and R. Bradford
  Download pdf
  

  Surveys

• Document Structure Analysis: A Survey
  Proc. of SPIE Conf. on Document Recognition and Retrieval, Santa Clara, CA, pp. 197-207, January 2003.
  by S. Mao, A. Rosenfeld, and T. Kanungo
  Download pdf
  
• Reconstruction of CAD Objects from Engineering Drawings: A Survey
  Proc. of First IAPR Workshop on Graphics Recognition University Park, PA, 1995, pp. 217-228
  by T. Kanungo, R. M. Haralick, and D. Dori
  Download ps pdf
  

  Volumes

• Document Recognition and Retrieval X
  SPIE, Belligham, WA, 2003.
  T. Kanungo, E. H. B. Smith, J. Hu, and P. B. Kantor (editors)
  
  
• Document Recognition and Retrieval IX
  SPIE, Belligham, WA, 2002.
  P. B. Kantor, J. Zhou, and T. Kanungo (editors)
  
  
• Special issue on --- Performance Evaluation: Theory, Practice and Impact
  Int. Journal of Document Analysis and Recognition, vol. 4, no. 3, 2002.
  by T. Kanungo, H. S. Baird and R. M. Haralick
  
  

  Software

• Open Source Software
  (Open source software I have been involved in.)
• OmniPage OCR Product
  (I worked on the multilingual OCR module when OmniPage was owned by Caere.)

  Multilingual OCR Workshop

  OCR Course