Skip to main content

Document analysis systems that improve with use

Abstract

Document analysis tasks for which representative labeled training samples are available have been largely solved. The next frontier is coping with hitherto unseen formats, unusual typefaces, idiosyncratic handwriting and imperfect image acquisition. Adaptive and style-constrained classification methods can overcome some expected variability, but human intervention will remain necessary in many tasks. Interactive pattern recognition includes data exploration and active learning as well as access to stored documents. The principle of “green interaction” is to make use of every intervention to reduce the likelihood that the automated system will make the same mistake again and again. Some of these techniques may pop up in forthcoming personal camera-based memex-like applications that will have a far broader range of input documents and scene text than the current, successful but highly specialized, systems for patents, postal addresses, bank checks and books.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22

References

  1. 1.

    Bush, V.: As We May Think. The Atlantic, Washington (1945)

    Google Scholar 

  2. 2.

    Nagy, G.: A Self-serving Review of My Own Work. In: IAPR Newsletter (2012)

  3. 3.

    Nagy, G.: Disruptive developments in document recognition. Pattern Recognit. Lett. 79, 106–112 (2015)

    Google Scholar 

  4. 4.

    Ascher, R.N., Koppelman, G., Miller, M.J., Nagy, G.: An interactive system for reading unformatted printed text. IEEE Trans. Comput. 20(12), 1527–1543 (1971)

    Google Scholar 

  5. 5.

    Casey, R.G., Nagy, G.: An autonomous reading machine. IEEE Trans. Comput. C-17(5), 492–503 (1968)

    Google Scholar 

  6. 6.

    Casey, R.G., Nagy, G.: Advances in pattern recognition. Sci. Am. 224(4), 56–71 (1971)

    Google Scholar 

  7. 7.

    Nagy, G., Seth, S., Einspahr, K.: Decoding substitution ciphers by means of word matching with application to OCR. IEEE Trans. Pattern Anal. Mach. Intell. 9(5), 710–715 (1987)

    Google Scholar 

  8. 8.

    Ho, T.K., Nagy, G.: OCR with no shape training. In: Proceedings of international conference on pattern recognition-XV, vol. 4, pp. 27–30, Barcelona, Spain (2000)

  9. 9.

    Blostein, D., Nagy, G.: Asymptotic cost in document conversion. Proc. SPIE 8297, Document Recognition and Retrieval XIX, 82970N (2012). https://doi.org/10.1117/12.912161

  10. 10.

    Zou, J., Nagy, G.: Human–computer interaction for complex pattern recognition problems. In: Basu, M., Ho, T.K. (eds.) Data Complexity in Pattern Recognition. Springer, London (2006)

    Google Scholar 

  11. 11.

    Chien, Y.T.: Interactive Pattern Recognition. Marcel Dekker Inc, New York (1970)

    Google Scholar 

  12. 12.

    Ball, G.H., Hall, D.J.: Some implications of interactive graphic computer systems for data analysis and statistics. Technometrics 12, 17–31 (1970)

    MATH  Google Scholar 

  13. 13.

    Sammon, J.W.: Interactive pattern analysis and classification. IEEE Trans. Comput. 19, 594–616 (1970)

    MATH  Google Scholar 

  14. 14.

    Tukey, J.: Exploratory data analysis. Addison-Wesley, Boston (1977)

    MATH  Google Scholar 

  15. 15.

    Gelsema, E.S.: Applications of interactive pattern recognition. In: Kittler, J., Fu, K.-S., Pau, L.F. (eds.) Pattern Recognition Theory and Applications, Proceedings of the NATO Advanced Study Institute, Oxford (1981)

  16. 16.

    Smit, J.W., Gelsema, E.S., Huiges, W., Nawrath, R.F., Halie, M.R.: A commercially available interactive pattern recognition system for the characterization of blood cells: description of the system, extraction and evaluation of simple geometrical parameters of normal white cells. Clin Lab Haematol 1(2), 109–119 (1979)

    Google Scholar 

  17. 17.

    Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs (1988)

    MATH  Google Scholar 

  18. 18.

    Siedlecki, W., Siedlecka, K., Sklansky, J.: An overview of mapping techniques for exploratory pattern analysis. Pattern Recognit. 21, 411–429 (1988)

    MathSciNet  MATH  Google Scholar 

  19. 19.

    Vesanto, J.: SOM-based data visualization methods. J. Intell. Data Anal. 3, 111–126 (1999)

    MATH  Google Scholar 

  20. 20.

    Ho, T.K., Mirage: A visual tool for scientific inquiries. In: Graham, M., Fitzpatrick, M., McGlynn, T. (eds.) The National Virtual Observatory: Tools And Techniques For Astronomical Research, Astronomical Society of the Pacific, ASP Conference Series, vol. CS-382, pp. 29–36 (2008)

  21. 21.

    Nagy, G., Zhang, X.: Simple statistics for complex feature spaces. In: Basu, M., Ho, T.K. (eds.) Data Complexity in Pattern Recognition. Springer, London (2006)

    Google Scholar 

  22. 22.

    Abbott, E.A., Flatland, A.: A Romance of Many Dimensions. Flatland, Seeley & Co. of London (1884)

  23. 23.

    Nagy, G.: Candide’s practical principles of experimental pattern recognition. IEEE Trans. Pattern Anal. Mach. Intell. 5(2), 199–200 (1983)

    Google Scholar 

  24. 24.

    Novotny, T.: Two challenges of correct validation in pattern recognition. Front. Robot. AI 25, 5 (2014)

    MathSciNet  Google Scholar 

  25. 25.

    Nagy, G.: Document image analysis: automated performance evaluation. In: Spitz, A.L., Dengel, A. (eds.) Document Analysis Systems, pp. 137–156. World Scientific, Singapore (1995)

    Google Scholar 

  26. 26.

    Rice, S., Nagy, G., Nartker, T.A.: Optical Character Recognition: An Illustrated Guide to the Frontier. Kluwer Academic Publishers, Boston (1999)

    Google Scholar 

  27. 27.

    Dietterich, T.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput. 10, 1895–1923 (1998)

    Google Scholar 

  28. 28.

    Baird, H.S.: Document image defect models and their uses. In: Proceedings of IAPR 2nd International Conference on Document Analysis & Recognition, Tsukuba Science City, Japan, October 20–22 (1993)

  29. 29.

    Li, Y., Lopresti, D., Nagy, G., Tomkins, A.: Validation of image defect models for optical character recognition. IEEE Trans. Pattern Anal. Mach. Intell. 18(2), 99–108 (1996)

    Google Scholar 

  30. 30.

    Sarkar, P., Lopresti, D., Zhou, J., Nagy, G.: Spatial sampling of printed patterns. IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 344–351 (1998)

    Google Scholar 

  31. 31.

    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., David, W.-F., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial networks. In: Proceedings of the international conference on neural information processing systems (NIPS 2014), pp. 2672–2680

  32. 32.

    Hu, J., Kashi, R., Lopresti, D., Nagy, G., Wilfong, G.: Why table ground-truthing is hard. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition, September 2001, Seattle, WA, pp. 129–133

  33. 33.

    Lopresti, D., Nagy, G.: Issues in ground-truthing graphic documents. In: Proceedings of the Fourth IAPR International Workshop on Graphics Recognition, September 2001, Kingston, Ontario, Canada, pp. 59–72

  34. 34.

    Lamiroy, B., Lopresti, D.: An open architecture for end-to-end document analysis benchmarking. In: Proceedings of International Conference on Document Analysis and Recognition, pp. 42–47 (2011)

  35. 35.

    Lewis, D.D., Gale, W.A.: A sequential algorithm for training text classifiers. In: Proceedings of 11th International Conference on Machine Learning, Morgan Kaufman, pp. 148–156 (1994)

    Google Scholar 

  36. 36.

    Schohn, G., Cohn, D.: Less is more: active learning with support vector machines. In: Proceedings of International Conference on Machine Learning (2000)

  37. 37.

    Dagan, I., Engelson, S.: Committee-based sampling for training probabilistic classifiers. In: International Conference on Machine Learning (1995)

  38. 38.

    Veeramachaneni, S., Avesani, P.: Active sampling for feature selection. In: Proceedings of Third IEEE International Conference on Data Mining, pp. 665–668 (2003)

  39. 39.

    Veeramachaneni, S., Olivetti, E., Avesani, P.: Active sampling for detecting irrelevant features. In: Proceedings of the 23rd International Conference on Machine learning, pp. 961–968 (2006)

  40. 40.

    Nagy, G.: Estimation, learning, and adaptation: systems that improve with use, S + SSPR 2012, Pierre Devijver Award Lecture, Springer LNCS 7626, pp. 1–12 (2012)

    Google Scholar 

  41. 41.

    Smith, R.: An overview of the tesseract OCR engine. In: Proceedigs of Document Analysis and Recognition ICDAR 2007, pp. 629–633. Curitiba, Brazil (2007)

  42. 42.

    Lipsky, L., Lopresti, D., Nagy, G.: Optimal policy for labeling training samples. In: Proceedings of Document Recognition and Retrieval XX (IS&T/SPIE International Symposium on Electronic Imaging), San Francisco, CA, pp. 865809-1–865809-9 (2013)

  43. 43.

    Gold, B.: Machine recognition of hand-sent Morse code. IRE Trans. Inf. Theory IT-5, 17–24 (1959)

    MathSciNet  Google Scholar 

  44. 44.

    Cooper, D.B., Cooper, P.W.: Nonsupervised adaptive signal detection and pattern recognition. Inf. Control 7(416444), 1964 (1964)

    MathSciNet  MATH  Google Scholar 

  45. 45.

    Fralick, S.C.: The synthesis of machines which learn without a teacher. Technical Report 6103-8, Stanford Electronics Lab., Stanford, California (1964)

  46. 46.

    Fralick, S.C.: Learning to recognize patterns without a teacher. IEEE Trans. Inf. Theory 13, 57–65 (1967)

    Google Scholar 

  47. 47.

    Braverman, E.M.: The method of potential functions in the problem of training machines to recognize patterns without a trainer. Autom. Remote Control 27, 1748–1771 (1966)

    MathSciNet  MATH  Google Scholar 

  48. 48.

    Dorofeyuk, A.A.: Teaching algorithm for a pattern recognition machine without a teacher, based on the method of potential functions. Autom. Remote Control 27, 1728–1737 (1966)

    Google Scholar 

  49. 49.

    Scudder, H.J.: Probability of error of some adaptive pattern recognition machines. IEEE Trans. Inf. Theory IT-11, 363–371 (1965)

    MathSciNet  MATH  Google Scholar 

  50. 50.

    Lucky, R.W.: Automatic equalization for digital communication. Bell Syst. Tech. J. 44, 547–588 (1965)

    MathSciNet  Google Scholar 

  51. 51.

    Lucky, R.W.: Techniques for adaptive equalization of digital communication systems. Bell Syst. Tech. J. 45, 255–286 (1966)

    Google Scholar 

  52. 52.

    Spragins, J.: Learning without a teacher. IEEE Trans. Inf. Theory IT-12, 223–229 (1966)

    Google Scholar 

  53. 53.

    Tsypkin, Y.Z. (ed.): Adaptation and Learning in Automatic Systems. Academic Press, New York (1971)

    MATH  Google Scholar 

  54. 54.

    Tsypkin, Ya.Z.: Adaptation, training, and self-organization in automatic systems. Autom. Remote Control 27, 1652 (1966)

    MathSciNet  Google Scholar 

  55. 55.

    Nagy, G., Shelton, G.L.: Self-corrective character recognition system. IEEE Trans. Inf. Theory 12(2), 215–222 (1966)

    Google Scholar 

  56. 56.

    Baird, H.S., Nagy, G.: A self-correcting 100-font classifier. In: Proceedings of SPIE Conference on Document Recognition, vol. SPIE-2181, pp. 106–115. San Jose, CA (1994)

  57. 57.

    Tsukuda, M., Iwamura, M., Kise, K.: Expanding recognizable distorted characters using self-corrective recognition. In: 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 327–332 (2012)

  58. 58.

    Iwamura, M., Tsukada, M., Kise, K.: Automatic labeling for scene text database. In: 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1365–1369 (2013)

  59. 59.

    Ho, Y.C., Agrawala, A.K.: On the self-learning scheme of Nagy and Shelton. Proc. IEEE 55, 1764–1765 (1967)

    Google Scholar 

  60. 60.

    Nagy, G., Tuong, N.G.: On a theoretical pattern recognition model of Ho and Agrawala. Proc. IEEE 56(6), 1108–1109 (1968)

    Google Scholar 

  61. 61.

    Marosi, I.: Industrial OCR approaches: architecture, algorithms and adaptation techniques. In: Proceedings of IS&T/SPIE Elecronic Imaging, DR&R. SPIE, vol. 6500, pp. 1–10 (2007)

  62. 62.

    Veeramachaneni, S., Nagy, G.: Adaptive classifiers for multisource OCR. Int. J. Doc. Anal. Recognit. 6(3), 154–166 (2004)

    Google Scholar 

  63. 63.

    Sarkar, P., Nagy, G.: Style consistent classification of isogenous patterns. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 88–98 (2005)

    Google Scholar 

  64. 64.

    Raviv, J.: Decision making in Markov chains applied to the problem of pattern recognition. IEEE Trans. Inf. Theory IT-13(4), 536–551 (1967)

    MathSciNet  Google Scholar 

  65. 65.

    Toussaint, G.T.: The use of context in pattern recognition. Pattern Recognit. 10, 189–204 (1978)

    MathSciNet  MATH  Google Scholar 

  66. 66.

    Zramdini, A.W., Ingold, R.: Optical font recognition using typographical features. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 877–882 (1998)

    Google Scholar 

  67. 67.

    Shi, H., Pavlidis, T.: Font recognition and contextual processing for more accurate text recognition. In: Proceedings of Fourth International Conference on Document Analysis and Recognition, vol. 1, pp. 39–44 (1997)

  68. 68.

    Marinai, S., Marino, E., Soda, E.G.: Font adaptive word indexing of modern printed documents. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1187–1199 (2006)

    Google Scholar 

  69. 69.

    Veeramachaneni, S., Sarkar, P., Nagy, G.: Modeling context as statistical dependence. In: Proceedings of Modeling and Using Context: 5th International and Interdisciplinary Conference CONTEXT 2005, Paris, France, Springer Lecture Notes in Computer Science, vol. 3554, pp. 515–528, July 5–8 (2005)

    MATH  Google Scholar 

  70. 70.

    Nagy, G., Veeramachaneni, S.: Adaptive and interactive approaches to document analysis. In: Marinai, S., Fujisawa, H. (eds.) Machine Learning in Document Analysis and Recognition. Studies in Computational Intelligence, vol. 90, pp. 221–257. Springer, Berlin (2008)

    Google Scholar 

  71. 71.

    Veeramachaneni, S., Nagy, G.: Style context with second order statistics. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 14–22 (2005)

    Google Scholar 

  72. 72.

    Veeramachaneni, S., Nagy, G.: Analytical results on style-constrained Bayesian classification of pattern fields. IEEE Trans. Pattern Anal. Mach. Intell. 29(7), 1280–1285 (2007)

    Google Scholar 

  73. 73.

    Klein, B., Dengel, A.: Problem-adaptable document analysis and understanding for high-volume applications. IJDAR 6(3), 167–180 (2003)

    Google Scholar 

  74. 74.

    Zhang, X.Y., Liu, C.-L.: Writer adaptation with style transfer mapping. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 35(7), 1773–1787 (2013)

    Google Scholar 

  75. 75.

    Computing Community Consortium and the Association for the Advancement of Artificial Intelligence. A 20-Year Community Roadmap for Artificial Intelligence Research in the US. https://cra.org/ccc/wp-content/uploads/sites/2/2019/08/17587_CCC-AI-Report_V7-1.pdf

  76. 76.

    Cirstea, B.-L., Likforman-Sulem, L.: Improving a deep convolutional neural network architecture for character recognition. In: Proceedimgs of Document Recognition and Retrieval, IS&T Electronic Imaging, no. 7, pp. 1–7 (2016)

  77. 77.

    Nagy, G., Wagle, S.: Approximation of polygonal thematic maps by cellular maps. Commun. ACM 22(9), 518–525 (1979)

    Google Scholar 

  78. 78.

    Nagy, G., Wagle, S.: Geographic data processing. ACM Comput. Surv. 11(2), 139–181 (1979)

    Google Scholar 

  79. 79.

    Nagy, G., Embley, D.W.: Behavioral aspects of text editors. ACM Comput. Surv. 13(1), 33–70 (1981)

    Google Scholar 

  80. 80.

    Nagy, G., Samal, A., Seth, S., Fisher, T., Guthman, E., Nagy, K.G., Samal, A., Seth, S., Fisher, T., Guthman, E., Kalafala, K., Li, L., Sarkar, P., Sivasubramaniam, S., Xu, Y.: A prototype for adaptive association of street names with streets on maps. In: Tombre, K., Chhabra, A. (eds.) Graphics Recognition: Algorithms and Systems. Springer Lecture Notes in Computer Science, pp. 302–313. Springer, Berlin (1998)

    Google Scholar 

  81. 81.

    Li, L., Nagy, G., Samal, A., Seth, S., Xu, Y.: Cooperative text and line-art extraction from a topographic map. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR-99), pp. 467–470. Bangalore, India (1999)

  82. 82.

    Nazari, N.H., Tan, T., Chiang, Y.-Y.: Free content integrating text recognition for overlapping text detection in maps. In: Proceedimgs of Document Recognition and Retrieval, IS&T Electronic Imaging, no. 8, pp. 1–8 (2016)

  83. 83.

    Nagy, G., Seth, S.: Hierarchical image representation with application to optically scanned documents. In: Proceedings of the Seventh International Conference on Pattern Recognition, pp. 347–349. Montreal (1984)

  84. 84.

    Nagy, G., Seth, S., Viswanathan, M.: A prototype document image analysis system for technical journals. IEEE Comput. 25, 10–22 (1992)

    Google Scholar 

  85. 85.

    Krishnamoorthy, M., Nagy, G., Seth, S., Viswanathan, M.: Syntactic segmentation and labeling of digitized pages from technical journals. IEEE Trans. Pattern Anal. Mach. Intell. 15(7), 737–747 (1993)

    Google Scholar 

  86. 86.

    Xu, Y., Nagy, G.: Prototype extraction and adaptive OCR. IEEE Trans. Pattern Anal. Mach. Intell. 21(12), 1280–1296 (1999)

    Google Scholar 

  87. 87.

    Nagy, G., Tamhankar, M.: VeriClick, an efficient tool for table format verification. In: Proceedings of SPIE/EIT/DRR. San Francisco (2012)

  88. 88.

    Zou, J., Nagy, G.: Visible models for interactive pattern recognition. Pattern Recognit. Lett. 28, 2335–2342 (2007)

    Google Scholar 

  89. 89.

    Evans, A., Sikorski, J., Thomas, P., Cha, S.-H., Tappert, C., Zou, G., Gattani, A., Nagy, G.: Computer assisted visual interactive recognition (CAVIAR) technology. In: 2005 IEEE International Conference on Electro-Information Technology, Lincoln, NE, (2005) (Proceedings on CD-ROM only)

  90. 90.

    Nagy, G., Lopresti, D.: Interactive document processing and digital libraries. In: Proceedings of 2nd IEEE International Conference on Document Image Analysis for Libraries, Lyon, France, April 27–28, pp. 1–9. IEEE Computer Society Press (2006)

  91. 91.

    Lopresti, D., Nagy, G., Barney Smith, E.: A document analysis system for supporting electronic voting research. In: Proceedings of Document Analysis Systems, Nara, Japan (2008)

  92. 92.

    Nagy, G., Lopresti, D., Barney Smith, E.H., Wu, Z.: Characterizing challenged Minnesota Ballots. In: Proceedings of Document Recognition and Retrieval. SPIE, San Jose (2011)

  93. 93.

    Nagy, G., Zhang, X.: CalliGUI: interactive labeling of calligraphic character images. In: Proceedings of ICDAR 11. Beijing (2011)

  94. 94.

    Embley, D.W., Nagy, G.: Green interaction for extracting family information from OCR’d books. In: Document Analysis Systems Workshop (DAS’18). Vienna (2018)

  95. 95.

    Nagy, G.: Green Information Extraction from Family Books, Springer Nature Computer Science (Accepted)

  96. 96.

    Nagy, G.: The lifetime reader. IEEE Pervasive Comput. 17(4), 86–95 (2018)

    Google Scholar 

  97. 97.

    Nagy, G.: Neural networks—then and now. IEEE Trans. Neural Netw. 2(2), 316–318 (1991)

    MathSciNet  Google Scholar 

  98. 98.

    Ouimette, D.: Digitizing the records in the granite mountain. SamilySearch. https://familysearch.org/learn/wiki/en/Digitizing_the_Records_in_the_Granite_Mountain. Accessed 4 Nov 2015

  99. 99.

    Koga, M., Mine, R., Kameyama, T., Takahashi, T., Yamazaki, M., Yamaguchi, T.: Camera-based Kanji OCR for mobile-phones: practical issues. In: Document Analysis and Recognition. Proceedings. Eighth International Conference 2, vol. 29, pp. 635–639 (2005)

  100. 100.

    Liang, J., Doermann, D., Li, H.: Camera-based analysis of text and documents: a survey. IJDAR 7(84), 84–104 (2005)

    Google Scholar 

  101. 101.

    Liang, J., DeMenthon, D., Doermann, D.: Geometric rectification of camera-captured document images. IEEE Trans. Pattern Anal. Mach. Intell. 30(4), 591–605 (2008)

    Google Scholar 

  102. 102.

    Liang, J., DeMenthon, D., Doermann, D.: Mosaicing of camera-captured document images. Comput. Vis. Image Underst. 113(4), 572–579 (2009)

    Google Scholar 

  103. 103.

    Moraleda, J., Hull, J.J.: Toward massive scalability in image matching. In: IAPR International Conference on Pattern Recognition (ICPR), pp. 3424–3427. Istanbul, Turkey, Aug. 23–26 (2010)

  104. 104.

    Ahmed, S., Kise, K., Iwamura, M., Liwicki, M., Dengel, A.: Automatic ground truth generation of camera captured documents using document image retrieval. In: ICDAR 2013, pp. 528–532

  105. 105.

    Nakai, T., Kise, K., Iwamura, M.: Camera-based document image retrieval as voting for partial signatures of projective invariants. In: 8th International Conference on Document Analysis and Recognition (ICDAR), pp. 379–383 (2005)

  106. 106.

    Toyama, T., Dengel, A., Suzuki, W., Kise, K.: Wearable reading assist system: augmented reality document combining document retrieval and eye tracking. In: 12th International Conference Document Analysis and Recognition (ICDAR), 2013 on 30–34 (2013)

  107. 107.

    Sabelman, E.E., Lam, R.: The real-life dangers of augmented reality. IEEE Spectr. 52(7), 48–53 (2015)

    Google Scholar 

  108. 108.

    Kimura, T., Huang, R., Uchida, S., Iwamura, M., Omachi, S., Kise, K.: The reading-life log—technologies to recognize texts that we read. In: ICDAR, pp. 91–95 2013

  109. 109.

    Kunze, K., Masai, K., Inami, M., Sacakli, Ö., Liwicki, M., Dengel, A., Ishimaru, S., Kise, K.: Quantifying reading habits: counting how many words you read. In: UbiComp, pp. 87–96 (2015)

  110. 110.

    Matsubara, M., Folz, J., Toyama, T., Liwicki, M., Dengel, A., Kise, K.: Extraction of read text using a wearable eye tracker for automatic video annotation. In: UbiComp/ISWC Adjunct, pp. 849–854 (2015)

  111. 111.

    Fujisawa, H., Sako, H., Okada, Y., Lee, S.-W.: Information capturing camera and developmental issues. In: Proceedings of International Conference on Document Analysis and Recognition, ICDAR’99, pp. 205–208. Bangalore, India, Sept. 20–22 (1999)

  112. 112.

    Iwamura, M., Kunze, K., Kato, Y., Utsumi, Y., Kise, K.: Haven’t we met before? A realistic memory assistance system to remind you of the person in front of you. Augment. Hum. Int. Conf. 32(1–32), 4 (2014)

    Google Scholar 

  113. 113.

    Cullen, J., Hull, J.J.: Oversize document copying system. In: IAPR Workshop on Document Analysis Systems. Malvern, Pennsylvania, October 14–16 (1996)

  114. 114.

    Frazer, I.: Got a bad memory? This company has you covered. Wall St Daily, Aug. 29 (2015)

  115. 115.

    Ascher, R.N., Nagy, G.: A means for achieving a high degree of compaction on scan-digitized printed text. IEEE Trans. Comput. 23(11), 1174–1179 (1974)

    MATH  Google Scholar 

  116. 116.

    Schone, P., Cannaday, A., Stewart, S., Day, R., Schone, J.: Automatic transcription of historical newsprint by leveraging the Kaldi speech recognition toolkit. In: Proceedimgs of Document Recognition and Retrieval, IS&T Electronic Imaging, no. 10, pp. 1–10 (2016)

  117. 117.

    Kobayashi, T., Iwamura, M., Matsuda, T., Kise, K.: An anytime algorithm for camera-based character recognition. In: 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 1140–1144 (2013)

  118. 118.

    Mantha, M., Chaithanya, J.K.: Vision based traffic panel text information and sign retrieval. International Journal of Current Engineering and Technology, vol. 5, no. 4 (2015). Available at http://inpressco.com/category/ijcet

  119. 119.

    Fujisawa, H., Hatakeyama, A., Higashino, J.: A personal universal filing system based on the concept-relation model. In: Proceedings of the 1st International Conference on Expert Database Systems, pp. 31–44. Charleston, SC (1986)

Download references

Acknowledgements

H. Fujisawa, P. Sarkar, A. Dengel, and three savvy IJDAR referees provided excellent suggestions. I am also grateful to the EICs of IJDAR, K. Kise, D. Lopresti and S. Marinai, who are (disclosure) old friends, for inviting me to ramble.

Author information

Affiliations

Authors

Corresponding author

Correspondence to George Nagy.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Nagy, G. Document analysis systems that improve with use. IJDAR 23, 13–29 (2020). https://doi.org/10.1007/s10032-019-00344-x

Download citation

Keywords

  • Interactive document analysis
  • Adaptive classification
  • Style-constrained recognition
  • Camera-based OCR
  • Memex
  • Lifetime reader