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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 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.
- 7.
References
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)
Popper, K.R.: The Logic of Scientific Discovery, Reprint edn. Routledge, New York (1992) (Original edition, 1934 “Logik der Forschung”)
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)
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
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)
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)
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)
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
Eco, U.: The Limits of Interpretation. Indiana University Press, Bloomington (1990)
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)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results (2011). http://www.pascal-network.org/challenges/VOC/voc2011/workshop/index.html
Voorhees, E., Harman, D., et al.: TREC: Experiment and Evaluation in Information Retrieval, vol. 63. MIT press, Cambridge (2005)
Mller, H., Clough, P., Deselaers, T., Caputo, B.: ImageCLEF: Experimental Evaluation in Visual Information Retrieval, 1st edn. Springer, Heidelberg (2010)
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))
Carlotto, M.J.: Effect of errors in ground truth on classification accuracy. Int. J. Remote Sens. 30(18), 4831–4849 (2009)
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)
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)
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)
Winn, J., Everingham, M.: The PASCAL visual object classes challenge 2007 (VOC2007) annotation guidelines (2007). http://PASCALlin.ecs.soton.ac.uk/challenges/VOC/VOC2007/guidelines.html
Tarantola, A.: Inverse Problem Theory and Methods for Model Parameter Estimation. Society for Industrial Mathematics, Philadelphia (2005)
Heidegger, M.: Being and Time. Library of Philosophy and Theology. Blackwell, Oxford (1967)
Peirce, C.S.: Syllabus: Nomenclature and Division of Triadic Relations, as far as they are determined. MS [R] 540 (1903)
Eco, U., Collini, S., Culler, J., Rorty, R., Brooke-Rose, C.: Interpretation and Overinterpretation. Tanner Lectures in Human Values. Cambridge University Press, Cambridge (1992)
Eco, U.: Dall’albero al labirinto: studi storici sul segno e l’interpretazione. Bompiani (2007)
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)
Ganter, B., Wille, R.: Formal Concept Analysis - Mathematical Foundations. Springer, Heidelberg (1999)
Ganter, B., Stumme, G., Wille, R. (eds.): Formal Concept Analysis. LNCS (LNAI), vol. 3626. Springer, Heidelberg (2005)
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)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Niblack, W.: An Introduction to Digital Image Processing. Strandberg Publishing Company, Birkeroed (1985)
Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recogn. 33(2), 225–236 (2000)
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)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lamiroy, B. (2014). Interpretation, Evaluation and the Semantic Gap ... What if We Were on a Side-Track?. In: Lamiroy, B., Ogier, JM. (eds) Graphics Recognition. Current Trends and Challenges. GREC 2013. Lecture Notes in Computer Science(), vol 8746. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-44854-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-662-44854-0_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44853-3
Online ISBN: 978-3-662-44854-0
eBook Packages: Computer ScienceComputer Science (R0)