Skip to main content
Top

2014 | OriginalPaper | Chapter

Interpretation, Evaluation and the Semantic Gap ... What if We Were on a Side-Track?

Author : Bart Lamiroy

Published in: Graphics Recognition. Current Trends and Challenges

Publisher: Springer Berlin Heidelberg

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

A significant amount of research in Document Image Analysis, and Machine Perception in general, relies on the extraction and analysis of signal cues with the goal of interpreting them into higher level information. This paper gives an overview on how this interpretation process is usually considered, and how the research communities proceed in evaluating existing approaches and methods developed for realizing these processes. Evaluation being an essential part to measuring the quality of research and assessing the progress of the state-of-the art, our work aims at showing that classical evaluation methods are not necessarily well suited for interpretation problems, or, at least, that they introduce a strong bias, not necessarily visible at first sight, and that new ways of comparing methods and measuring performance are necessary. It also shows that the infamous Semantic Gap seems to be an inherent and unavoidable part of the general interpretation process, especially when considered within the framework of traditional evaluation. The use of Formal Concept Analysis is put forward to leverage these limitations into a new tool to the analysis and comparison of interpretation contexts.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Footnotes
3
This is a somewhat strong statement, and in many cases it can be helpful to use these functions anyway, as an instance of common practice in experimental research: “If we cannot immediately solve the global problem, let’s try and solve a more manageable sub-problem.”
 
4
We are making the implicit assumption that interpretations are mutually exclusive. Although this may seem restrictive, it is not. In cases where multiple interpretations are acceptable, one can simply replace \(\mathcal I\) by \(\left\{ 0,1\right\} ^{\left| I\right| }\).
 
5
This fuzzy distinction between syntax, semiosis and semantics is actually what troubled interpretation of hieroglyphs [25].
 
6
Results by Z. Jiang, M.Eng. student at Mines Nancy, France.
 
Literature
1.
go back to reference Lamiroy, B., Lopresti, D.: An open architecture for end-to-end document analysis benchmarking. In: 11th International Conference on Document Analysis and Recognition - ICDAR 2011, Beijing, China, pp. 42–47. IEEE Computer Society (2011) Lamiroy, B., Lopresti, D.: An open architecture for end-to-end document analysis benchmarking. In: 11th International Conference on Document Analysis and Recognition - ICDAR 2011, Beijing, China, pp. 42–47. IEEE Computer Society (2011)
2.
go back to reference Popper, K.R.: The Logic of Scientific Discovery, Reprint edn. Routledge, New York (1992) (Original edition, 1934 “Logik der Forschung”) Popper, K.R.: The Logic of Scientific Discovery, Reprint edn. Routledge, New York (1992) (Original edition, 1934 “Logik der Forschung”)
3.
go back to reference Lamiroy, B., Lopresti, D.: A platform for storing, visualizing, and interpreting collections of noisy documents. In: Fourth Workshop on Analytics for Noisy Unstructured Text Data - AND’10, Toronto, Canada. ACM International Conference Proceeding Series. ACM (2010) Lamiroy, B., Lopresti, D.: A platform for storing, visualizing, and interpreting collections of noisy documents. In: Fourth Workshop on Analytics for Noisy Unstructured Text Data - AND’10, Toronto, Canada. ACM International Conference Proceeding Series. ACM (2010)
4.
go back to reference 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, Seattle, WA, pp. 129–133, September 2001 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, Seattle, WA, pp. 129–133, September 2001
5.
go back to reference Lopresti, D., Nagy, G., Smith, E.B.: Document analysis issues in reading optical scan ballots. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 105–112. ACM (2010) Lopresti, D., Nagy, G., Smith, E.B.: Document analysis issues in reading optical scan ballots. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 105–112. ACM (2010)
6.
go back to reference Smith, E.H.B.: An analysis of binarization ground truthing. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 27–34. ACM (2010) Smith, E.H.B.: An analysis of binarization ground truthing. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 27–34. ACM (2010)
7.
go back to reference Clavelli, A., Karatzas, D., Lladós, J.: A framework for the assessment of text extraction algorithms on complex colour images. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 19–26. ACM (2010) Clavelli, A., Karatzas, D., Lladós, J.: A framework for the assessment of text extraction algorithms on complex colour images. In: Proceedings of the 8th IAPR International Workshop on Document Analysis Systems, Boston, MA, USA, pp. 19–26. ACM (2010)
8.
go back to reference Lopresti, D., Nagy, G.: Issues in ground-truthing graphic documents. In: Proceedings of the Fourth IAPR International Workshop on Graphics Recognition, Kingston, Ontario, Canada, pp. 59–72, September 2001 Lopresti, D., Nagy, G.: Issues in ground-truthing graphic documents. In: Proceedings of the Fourth IAPR International Workshop on Graphics Recognition, Kingston, Ontario, Canada, pp. 59–72, September 2001
9.
go back to reference Eco, U.: The Limits of Interpretation. Indiana University Press, Bloomington (1990) Eco, U.: The Limits of Interpretation. Indiana University Press, Bloomington (1990)
10.
go back to reference Smeulders, A.W., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000)CrossRef Smeulders, A.W., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000)CrossRef
12.
go back to reference Voorhees, E., Harman, D., et al.: TREC: Experiment and Evaluation in Information Retrieval, vol. 63. MIT press, Cambridge (2005) Voorhees, E., Harman, D., et al.: TREC: Experiment and Evaluation in Information Retrieval, vol. 63. MIT press, Cambridge (2005)
13.
go back to reference Mller, H., Clough, P., Deselaers, T., Caputo, B.: ImageCLEF: Experimental Evaluation in Visual Information Retrieval, 1st edn. Springer, Heidelberg (2010)CrossRef Mller, H., Clough, P., Deselaers, T., Caputo, B.: ImageCLEF: Experimental Evaluation in Visual Information Retrieval, 1st edn. Springer, Heidelberg (2010)CrossRef
14.
go back to reference Valveny, E., Dosch, P., Fornés, A., Escalera, S.: Report on the third contest on symbol recognition. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) GREC 2007. LNCS, vol. 5046, pp. 321–328. Springer, Heidelberg (2008). (French Techno-Vision program (Ministry of Research) Spanish project TIN2006-15694-C02-02 Spanish research program Consolider Ingenio 2010:MIPRCV (CSD2007-00018)) Valveny, E., Dosch, P., Fornés, A., Escalera, S.: Report on the third contest on symbol recognition. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) GREC 2007. LNCS, vol. 5046, pp. 321–328. Springer, Heidelberg (2008). (French Techno-Vision program (Ministry of Research) Spanish project TIN2006-15694-C02-02 Spanish research program Consolider Ingenio 2010:MIPRCV (CSD2007-00018))
15.
go back to reference Carlotto, M.J.: Effect of errors in ground truth on classification accuracy. Int. J. Remote Sens. 30(18), 4831–4849 (2009)CrossRef Carlotto, M.J.: Effect of errors in ground truth on classification accuracy. Int. J. Remote Sens. 30(18), 4831–4849 (2009)CrossRef
16.
go back to reference Lopresti, D.P., Nagy, G.: Adapting the turing test for declaring document analysis problems solved. In: Blumenstein, M., Pal, U., Uchida, S., eds.: Document Analysis Systems, pp. 1–5. IEEE, New York (2012) Lopresti, D.P., Nagy, G.: Adapting the turing test for declaring document analysis problems solved. In: Blumenstein, M., Pal, U., Uchida, S., eds.: Document Analysis Systems, pp. 1–5. IEEE, New York (2012)
17.
go back to reference Lamiroy, B., Sun, T.: Computing precision and recall with missing or uncertain ground truth. In: Kwon, Y.-B., Ogier, J.-M. (eds.) GREC 2011. LNCS, vol. 7423, pp. 149–162. Springer, Heidelberg (2013) Lamiroy, B., Sun, T.: Computing precision and recall with missing or uncertain ground truth. In: Kwon, Y.-B., Ogier, J.-M. (eds.) GREC 2011. LNCS, vol. 7423, pp. 149–162. Springer, Heidelberg (2013)
18.
go back to reference Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)CrossRef Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)CrossRef
20.
go back to reference Tarantola, A.: Inverse Problem Theory and Methods for Model Parameter Estimation. Society for Industrial Mathematics, Philadelphia (2005)CrossRefMATH Tarantola, A.: Inverse Problem Theory and Methods for Model Parameter Estimation. Society for Industrial Mathematics, Philadelphia (2005)CrossRefMATH
21.
go back to reference Heidegger, M.: Being and Time. Library of Philosophy and Theology. Blackwell, Oxford (1967) Heidegger, M.: Being and Time. Library of Philosophy and Theology. Blackwell, Oxford (1967)
22.
go back to reference Peirce, C.S.: Syllabus: Nomenclature and Division of Triadic Relations, as far as they are determined. MS [R] 540 (1903) Peirce, C.S.: Syllabus: Nomenclature and Division of Triadic Relations, as far as they are determined. MS [R] 540 (1903)
23.
go back to reference Eco, U., Collini, S., Culler, J., Rorty, R., Brooke-Rose, C.: Interpretation and Overinterpretation. Tanner Lectures in Human Values. Cambridge University Press, Cambridge (1992)CrossRef Eco, U., Collini, S., Culler, J., Rorty, R., Brooke-Rose, C.: Interpretation and Overinterpretation. Tanner Lectures in Human Values. Cambridge University Press, Cambridge (1992)CrossRef
24.
go back to reference Eco, U.: Dall’albero al labirinto: studi storici sul segno e l’interpretazione. Bompiani (2007) Eco, U.: Dall’albero al labirinto: studi storici sul segno e l’interpretazione. Bompiani (2007)
25.
go back to reference Champollion, J.: Précis du système hiéroglyphique des anciens égyptiens, ou recherches sur les élémens premiers de cette écriture sacrée, sur leurs diverses combinaisons, et sur les rapports de ce système avec les autres méthodes graphiques égyptiennes. Imprimerie royale (1828) Champollion, J.: Précis du système hiéroglyphique des anciens égyptiens, ou recherches sur les élémens premiers de cette écriture sacrée, sur leurs diverses combinaisons, et sur les rapports de ce système avec les autres méthodes graphiques égyptiennes. Imprimerie royale (1828)
26.
go back to reference Ganter, B., Wille, R.: Formal Concept Analysis - Mathematical Foundations. Springer, Heidelberg (1999)CrossRefMATH Ganter, B., Wille, R.: Formal Concept Analysis - Mathematical Foundations. Springer, Heidelberg (1999)CrossRefMATH
27.
go back to reference Ganter, B., Stumme, G., Wille, R. (eds.): Formal Concept Analysis. LNCS (LNAI), vol. 3626. Springer, Heidelberg (2005) Ganter, B., Stumme, G., Wille, R. (eds.): Formal Concept Analysis. LNCS (LNAI), vol. 3626. Springer, Heidelberg (2005)
28.
go back to reference Coustaty, M., Bertet, K., Visani, M., Ogier, J.M.: A new adaptive structural signature for symbol recognition by using a Galois lattice as a classifier. IEEE Trans. Syst. Man Cybern. B 41(4), 1136–1148 (2011)CrossRef Coustaty, M., Bertet, K., Visani, M., Ogier, J.M.: A new adaptive structural signature for symbol recognition by using a Galois lattice as a classifier. IEEE Trans. Syst. Man Cybern. B 41(4), 1136–1148 (2011)CrossRef
29.
go back to reference Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)MathSciNetCrossRef Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)MathSciNetCrossRef
30.
go back to reference Niblack, W.: An Introduction to Digital Image Processing. Strandberg Publishing Company, Birkeroed (1985) Niblack, W.: An Introduction to Digital Image Processing. Strandberg Publishing Company, Birkeroed (1985)
31.
go back to reference Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recogn. 33(2), 225–236 (2000)CrossRef Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recogn. 33(2), 225–236 (2000)CrossRef
32.
go back to reference Wolf, C., Jolion, J.M., Chassaing, F.: Text localization, enhancement and binarization in multimedia documents. In: Proceedings of the International Conference on Pattern Recognition, vol. 2, pp. 1037–1040 (2002) Wolf, C., Jolion, J.M., Chassaing, F.: Text localization, enhancement and binarization in multimedia documents. In: Proceedings of the International Conference on Pattern Recognition, vol. 2, pp. 1037–1040 (2002)
33.
go back to reference Lahcen, B., Kwudia, L.K.: Lattice miner: a tool for concept lattice construction and exploration. In: Supplementary Proceeding of International Conference on Formal concept analysis (ICFCA’10) (2010) Lahcen, B., Kwudia, L.K.: Lattice miner: a tool for concept lattice construction and exploration. In: Supplementary Proceeding of International Conference on Formal concept analysis (ICFCA’10) (2010)
Metadata
Title
Interpretation, Evaluation and the Semantic Gap ... What if We Were on a Side-Track?
Author
Bart Lamiroy
Copyright Year
2014
Publisher
Springer Berlin Heidelberg
DOI
https://doi.org/10.1007/978-3-662-44854-0_17

Premium Partner