Abstract
Symbol spotting systems are intended to retrieve regions of interest from a document image database where the queried symbol is likely to be found. They shall have the ability to recognize and locate graphical symbols in a single step. In this paper, we present a set of measures to evaluate the performance of a symbol spotting system in terms of recognition abilities, location accuracy and scalability. We show that the proposed measures allow to determine the weaknesses and strengths of different methods. In particular we have tested a symbol spotting method based on a set of four different off-the-shelf shape descriptors.
Similar content being viewed by others
References
Aksoy, S., Ye, M., Schauf, M., Song, M., Wang, Y., Haralick, R.: Algorithm performance contest. In: Proceedings of the Fifteenth International Conference on Pattern Recognition, ICPR00, pp. 870–876 (2000). doi:10.1109/ICPR.2000.903054
Antonacopoulos, A., Bridson, D.: Performance analysis framework for layout analysis methods. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, ICDAR07, pp. 1258–1262 (2007). doi:10.1109/ICDAR.2007.4377117
Antonacopoulos, A., Gatos, B., Bridson, D.: ICDAR 2005 page segmentation competition. In: Proceedings of the Eighth International Conference on Document Analysis and Recognition, ICDAR05, pp. 75–79 (2005). doi:10.1109/ICDAR.2005.184
Antonacopoulos, A., Gatos, B., Bridson, D.: ICDAR 2007 page segmentation competition. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, ICDAR07, pp. 1279–1283 (2007) doi:10.1109/ICDAR.2007.203
Antonacopoulos, A., Gatos, B., Karatzas, D.: ICDAR 2003 page segmentation competition. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition, ICDAR03, pp. 688–692 (2003). doi:10.1109/ICDAR.2003.1227750
Antonacopoulos, A., Karatzas, D., Bridson, D.: Ground truth for layout analysis performance evaluation. In: Document Analysis Systems, DAS06. Lecture Notes on Computer Science, vol. 3872, pp. 302–311. Springer, Berlin (2006). doi:10.1007/11669487_27
Barber C., Dobkin D., Huhdanpaa H.: The quickhull algorithm for convex hulls. ACM Transactions on Mathematical Software 22(4), 469–483 (1996). doi:10.1145/235815.235821
Buckland M., Gey F.: The relationship between recall and precision. J. Am. Soc. Inform. Sci. 45(1), 12–19 (1994)
Davis, J., Goadrich, M.: The relationship between precision–recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 233–240 (2006). doi:10.1145/1143844.1143874
Delalandre, M., Pridmore, T., Valveny, E., Locteau, H., Trupin, E.: Building synthetic graphical documents for performance evaluation. In: Graphics Recognition. Recent Advances and New Opportunities. Lecture Notes on Computer Science, vol. 5046, pp. 288–298. Springer, Berlin (2008). doi:10.1007/978-3-540-88188-9_27
Fawcett T.: An introduction to ROC analysis. Pattern Recognit. Lett. 27(8), 861–874 (2006). doi:10.1016/j.patrec.2005.10.010
Holz, F., Witschel, H., Heinrich, G., Heyer, G., Teresniak, S.: An evaluation framework for semantic search in p2p networks. In: Proceedings of the Seventh International Workshop on Innovative Internet Community Systems, I2CS07 (2007)
Hripcsak G., Rothschild A.: Agreement, the F-measure, and reliability in information retrieval. J. Am. Med. Inform. Assoc 12(3), 296–298 (2005). doi:10.1016/j.jamia.2005.01.008
Hu M.: Visual pattern recognition by moment invariants. IRE Trans. Inform. Theory 8, 179–187 (1962)
Huijsmans D., Sebe N.: How to complete performance graphs in content-based image retrieval: add generality and normalize scope. IEEE Trans. Pattern Anal. Mach. Intell. 27(2), 245–251 (2005). doi:10.1109/TPAMI.2005.30
Kang, B., Kim, H., Lee, S.: Performance analysis of semantic indexing in text retrieval. In: Computational Linguistics and Intelligent Text Processing. Lecture Notes on Computer Science, vol. 2945, pp. 433–436. Springer, Berlin (2004).doi:10.1007/b95558
Kauppinen H., Seppänen T., Pietikäinen M.: An experimental comparison of autoregressive and fourier-based descriptors in 2d shape classification. IEEE Trans. Pattern Anal. Mach. Intell. 17, 201–207 (1995). doi:10.1109/34.368168
Lambert, G., Gao, H.: Discrimination properties of invariants using the line moments of vectorized contours. In: Proceedings of the 13th International Conference on Pattern Recognition, ICPR96, pp. 735–739 (1996). doi:10.1109/ICPR.1996.546920
Liu W., Dori D.: A protocol for performance evaluation of line detection algorithms. Mach. Vis. Appl. 9(5), 240–250 (1997). doi:10.1007/s001380050045
Liu W., Dori D.: Incremental arc segmentation algorithm and its evaluation. IEEE Trans. Pattern Anal.Mach. Intell. 20(4), 424–431 (1998). doi:10.1109/34.677280
Lopresti, D., Nagy, G.: Issues in ground-truthing graphic documents. In: Graphics Recognition Algorithms and Applications. Lecture Notes on Computer Science, vol. 2390, pp. 46–66. Springer, Berlin (2001). doi:10.1007/3-540-45868-9
Lu, C., Shukla, M., Subramanya, S., Wu, Y.: Performance evaluation of desktop search engines. In: Proceedings of the IEEE International Conference on Information Reuse and Integration, IRI07, pp. 110–115 (2007). doi:10.1109/IRI.2007.4296606
Lucas, S.: ICDAR 2005 text locating competition results. In: Proceedings of the Eighth International Conference on Document Analysis and Recognition, ICDAR05, pp. 80–84 (2005). doi:10.1109/ICDAR.2005.231
Lucas S., Panaretos A., Sosa L., Tang A., Wong S., Young R., Ashida K., Nagai H., Okamoto M., Yamamoto H., Miyao H., Zhu J., Ou W., Wolf C., Jolion J., Todoran L., Worring M., Lin X.: ICDAR 2003 robust reading competitions: entries, results, and future directions. Int. J. Doc. Anal. Recognit. 7(2), 105–122 (2005). doi:10.1007/s10032-004-0134-3
Makhoul, J., Kubala, F., Schwartz, R., Weischedel, R.: Performance measures for information extraction. In: Proceedings of DARPA Broadcast News Workshop (1999)
Marcus, J.: A novel algorithm for HMM word spotting performance evaluation and error analysis. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP92, pp. 89–92 (1992). doi:10.1109/ICASSP.1992.226113
Müller H., Müller W., Squire D., Marchand-Maillet S., Pun T.: Performance evaluation in content-based image retrieval: overview and proposals. Pattern Recognit. Lett. 22(5), 593–601 (2001). doi:10.1016/S0167-8655(00)00118-5
Neumann, T., Bender, M., Michel, S., Weikum, G.: A reproducible benchmark for P2P retrieval. In: Proceedings of the First International Workshop on Performance and Evaluation of Data Management Systems, ExpDB06, pp. 1–8 (2006)
Phillips I., Chhabra A.: Empirical performance evaluation of graphics recognition systems. IEEE Trans. Pattern Anal. Mach. Intell. 21(9), 849–870 (1999). doi:10.1109/34.790427
Rath, T., Manmatha, R.: Features for word spotting in historical manuscripts. In: Proceedings of the Seventh International Conf. on Document Analysis and Recognition, ICDAR03, pp. 218–222 (2003). doi:10.1109/ICDAR.2003.1227662
van Rijsbergen C.: Information Retrieval. Butterworth-Heinemann Newton, MA, USA (1979)
Rusiñol, M., Lladós, J.: Word and symbol spotting using spatial organization of local descriptors. In: The Eighth IAPR International Workshop on Document Analysis Systems, DAS08, pp. 489–496 (2008). doi:10.1109/DAS.2008.24
Smeaton, A., Over, P., Kraaij, W.: Evaluation campaigns and TRECVid. In: Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, pp. 321–330 (2006). doi:10.1145/1178677.1178722
Song J., Su F., Tai C., Cai S.: An object-oriented progressive-simplification-based vectorization system for engineering drawings: Model, algorithm, and performance. IEEE Trans. Pattern Anal. Mach. Intell. 24(8), 1048–1060 (2002). doi:10.1109/TPAMI.2002.1023802
Stoyan D., Stoyan H.: Fractals, Random Shapes and Point Fields (Methods of Geometrical Statistics). John Wiley & Sons, Chichester (1994)
Tabbone, S., Zuwala, D.: An indexing method for graphical documents. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition, ICDAR07, pp. 789–793 (2007). doi:10.1109/ICDAR.2007.4377023
Tombre, K., Lamiroy, B.: Graphics recognition—from re-engineering to retrieval. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition, ICDAR03, pp. 148–155 (2003)
Valveny, E., Dosch, P.: Symbol recognition contest: a synthesis. In: Graphics Recognition, Recent Advances and Perspectives. Lecture Notes on Computer Science, vol. 3088, pp. 368–385. Springer, Berlin (2004). doi:10.1007/b99011
Valveny, E., Dosch, P.: Report on the second symbol recognition contest. In: Graphics Recognition. Ten Years Review and Future Perspectives. Lecture Notes on Computer Science, vol. 3926, pp. 381–397. Springer, Berlin (2006). doi:10.1007/11767978
Valveny E., Dosch P., Winstanley A., Zhou Y., Yang S., Yan L., Liu W., Elliman D., Delalandre M., Trupin E., Adam S., Ogier J.: A general framework for the evaluation of symbol recognition methods. Int. J. Doc. Anal. Recognit. 9(1), 59–74 (2007). doi:10.1007/s10032-006-0033-x
Wolf C., Jolion J.: Object count/area graphs for the evaluation of object detection and segmentation algorithms. Int. J. Doc. Anal. Recognit. 8(4), 280–296 (2006). doi:10.1007/s10032-006-0014-0
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rusiñol, M., Lladós, J. A performance evaluation protocol for symbol spotting systems in terms of recognition and location indices. IJDAR 12, 83–96 (2009). https://doi.org/10.1007/s10032-009-0083-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-009-0083-y