Abstract
This paper presents an empirical study on the application of ranking fusion methods in the context of handwriting information retrieval. Several works in the electronic text-domain suggest that significant improvements in retrieval performance can be achieved by combining different approaches to IR. In the handwritten-domain, two quite different families of retrieval approaches are encountered. The first family is based on standard approaches carried out on texts obtained through handwriting recognition, therefore regarded as noisy texts, while the second one is recognition-free using word spotting algorithms. Given the large differences that exist between these two families of approaches (document and query representations, matching methods, etc.), we hypothesize that fusion methods applied to the handwritten-domain can also bring significant effectiveness improvements. Results show that for texts having a word error rate (wer) lower than 23%, the performances achieved with the combined system are close to the performances obtained with clean digital texts, i.e. without transcription errors. In addition, for poorly recognized texts (wer > 52%), improvements can also be obtained with standard fusion methods. Furthermore, we present a detailed analysis of the fusion performances, and show that existing indicators of expected improvements are not accurate in our context.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Shaw, J.A., Fox, E.A.: Combination of Multiple Searches. In: TREC-2, Proceedings of the 2nd Text REtrieval Conference, pp. 243–252 (1994)
Savoy, J., Le Calvé, A., Vrajitoru, D.: Report on the TREC-5 Experiment: Data fusion and Collection Fusion. In: TREC-5, Proceedings of the 5th Text Retrieval Conference, pp. 489–502 (1997)
Vogt, C.C., Cottrell, G.W.: Fusion via a Linear Combination of Scores. Information Retrieval 1(3), 151–173 (1999)
Aslam, J.A., Montague, M.: Models for Metasearch. In: SIGIR 2001, Proceedings of the 24th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 276–284 (2001)
Manmatha, R., Rath, T.M., Feng, F.: Modeling Score Distributions for Combining the Outputs of Search Engines. In: SIGIR 2001, Proceedings of the 24th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 267–275 (2001)
Montague, M., Aslam, J.A.: Condorcet Fusion for Improved Retrieval. In: CIKM 2001, Proceedings of the 11th International Conference on Information & Knowledge Management, pp. 538–548 (2002)
Renda, M.E., Straccia, U.: Web Metasearch: Rank vs. Score Based Rank Aggregation Methods. In: SAC 2003, Proceedings of the 18th Annual ACM Symposium on Applied Computing, pp. 841–846 (2003)
Wu, S., McClean, S.: Data Fusion with Correlation Weights. In: Losada, D.E., Fernández-Luna, J.M. (eds.) ECIR 2005. LNCS, vol. 3408, pp. 275–286. Springer, Heidelberg (2005)
Farah, M., Vanderpooten, D.: An Outranking Approach for Rank Aggregation in Information Retrieval. In: SIGIR 2007, Proceedings of the 30th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 591–598 (2007)
Belkin, N.J., Cool, C., Croft, W.B., Callan, J.P.: The E_ect of Multiple Query Representations on Information Retrieval System Performance. In: SIGIR 1993, Proceedings of the 16th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 339–346 (1993)
Lee, J.H.: Analysis of Multiple Evidence Combination. In: SIGIR 1997, Proceedings of the 20th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 267–276 (1997)
Beitzel, S.M., Jensen, E.C., Chowdury, A., Grossman, D., Frieder, O., Goharian, N.: On Fusion of Effective Retrieval Strategies in the Same Information Retrieval System. Journal of the American Society of Information Science & Technology 50(10), 859–868 (2004)
Plamondon, R., Srihari, S.N.: On-line and o_-line handwriting recognition: a comprehensive survey. IEEE Transactions on Pattern Analysis & Machine Intelligence 22(1), 63–84 (2000)
Russell, G., Perrone, M., Chee, Y.M.: Handwritten document retrieval. In: Proceedings of the 8th International Workshop on Frontiers in Handwriting Recognition, pp. 233–238 (2002)
Rath, T.M., Manmatha, R.: Word image matching using dynamic time warping. In: CVPR 2003, Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, pp. 521–527 (2003)
Jain, A.K., Namboodiri, A.M.: Indexing and retrieval of on-line handwritten documents. In: ICDAR 2003, Proceedings of the 10th International Conference on Document Analysis & Recognition, pp. 655–659 (2003)
Rath, T.M., Manmatha, R., Lavrenko, V.: A search engine for historical manuscript images. In: SIGIR 2004, Proceedings of the 27th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 369–376 (2004)
Vinciarelli, A.: Application of information retrieval techniques to single writer documents. Pattern Recognition Letters 26(14), 2262–2271 (2005)
Jawahar, C.V., Balasubramanian, A., Meshesha, M., Namboodiri, A.M.: Retrieval of online handwriting by synthesis and matching. Pattern Recognition 42(7), 1445–1457 (2009)
Terasawa, K., Tanaka, Y.: Slit style HOG feature for document image word spotting. In: ICDAR 2009, Proceedings of 10th International Conference on Document Analysis & Recognition, pp. 116–120 (2009)
Cheng, C., Zhu, B., Chen, X., Nakagawa, M.: Improvements in keyword search japanese characters within handwritten digital ink. In: ICDAR 2009, Proceedings of 10th International Conference on Document Analysis & Recognition, pp. 863–866 (2009)
Hull, D.A., Pedersen, J.O., Schütze, H.: Method Combination For Document Filtering. In: SIGIR 1996, Proceedings of the 19th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 279–287 (1996)
Sanderson, M.: Word sense disambiguation and information retrieval. In: SIGIR 1994, Proceedings of the 17th Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 142–151 (1994)
Robertson, S.E., Spärck Jones, K.: Relevance weighting of search terms. Journal of the American Society for Information Science 27(3), 129–146 (1976)
Ide, E.: New Experiments in Relevance Feedback. In: The Smart Retrieval System, pp. 337–354. Prentice-Hall, Inc., Englewood Cliffs (1971)
Perraud, F., Viard-Gaudin, C., Morin, E., Lallican, P.M.: Statistical language models for on-line handwriting recognition. IEICE Transactions on Information & Systems E88-D(8), 1807–1814 (2005)
Buckley, C., Voorhees, E.M.: Evaluating evaluation measure stability. In: SIGIR 2000, Proceedings of the 23rd Annual ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 33–40 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peña Saldarriaga, S., Morin, E., Viard-Gaudin, C. (2010). Ranking Fusion Methods Applied to On-Line Handwriting Information Retrieval. In: Gurrin, C., et al. Advances in Information Retrieval. ECIR 2010. Lecture Notes in Computer Science, vol 5993. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12275-0_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-12275-0_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12274-3
Online ISBN: 978-3-642-12275-0
eBook Packages: Computer ScienceComputer Science (R0)