Abstract
Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Almazan, J., Gordo, A., Fornés, A., Valveny, E.: Handwritten word spotting with corrected attributes. In: ICCV (2013)
Almazán, J., Gordo, A., Fornés, A., Valveny, E.: Word spotting and recognition with embedded attributes. IEEE TPAMI 36, 2552–2566 (2014)
Antonacopoulos, A., Downton, A.C.: Special issue on the analysis of historical documents (2007)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. JMLR (2012)
Biswas, S., Banerjee, A., Lladós, J., Pal, U.: DocSegTr: an instance-level end-to-end document image segmentation transformer. arXiv preprint arXiv:2201.11438 (2022)
Biswas, S., Riba, P., Lladós, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. (IJDAR) 24(3), 269–281 (2021)
Biswas, S., Riba, P., Lladós, J., Pal, U.: DocSynth: a layout guided approach for controllable document image synthesis. In: ICDAR (2021)
Bunke, H., Varga, T.: Off-line roman cursive handwriting recognition. In: Chaudhuri, B.B. (ed.) Digital Document Processing, pp. 165–183. Springer, London (2007). https://doi.org/10.1007/978-1-84628-726-8_8
Choudhary, A., Rishi, R., Ahlawat, S.: A new character segmentation approach for off-line cursive handwritten words. Proc. Comput. Sci. 17, 88–95 (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Howe, N.R.: Part-structured inkball models for one-shot handwritten word spotting. In: ICDAR (2013)
Kang, L., Riba, P., Rusinol, M., Fornés, A., Villegas, M.: Distilling content from style for handwritten word recognition. In: ICFHR (2020)
Kang, L., Riba, P., Rusinol, M., Fornés, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE TPAMI (2021)
Kang, L., Riba, P., Wang, Y., Rusiñol, M., Fornés, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 273–289. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58592-1_17
Konidaris, T., Kesidis, A.L., Gatos, B.: A segmentation-free word spotting method for historical printed documents. Pattern Anal. Appl. 19, 963–976 (2016)
Kozielski, M., Matysiak, M., Doetsch, P., Schlöter, R., Ney, H.: Open-lexicon language modeling combining word and character levels. In: ICFHR (2014)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350, 1332–1338 (2015)
Lombardi, F., Marinai, S.: Deep learning for historical document analysis and recognition-a survey. J. Imaging 6, 110 (2020)
Marcelli, A., Parziale, A., Senatore, R.: Some observations on handwriting from a motor learning perspective. In: AFHA (2013)
Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. IJDAR 5, 39–46 (2002)
Parziale, A., Capriolo, G., Marcelli, A.: One step is not enough: a multi-step procedure for building the training set of a query by string keyword spotting system to assist the transcription of historical document. J. Imaging 6, 109 (2020)
Poznanski, A., Wolf, L.: CNN-N-gram for handwriting word recognition. In: CVPR (2016)
Puigcerver, J., Toselli, A.H., Vidal, E.: Querying out-of-vocabulary words in lexicon-based keyword spotting. Neural Comput. Appl. 28, 2373–2382 (2017)
Rath, T.M., Manmatha, R.: Word spotting for historical documents. IJDAR 9, 139–152 (2007)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)
Sanchez, J.A., Toselli, A.H., Romero, V., Vidal, E.: ICDAR 2015 competition HTRtS: Handwritten text recognition on the transcriptorium dataset. In: ICDAR (2015)
Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recogn. 33, 225–236 (2000)
Shaffi, N., Hajamohideen, F.: Few-shot learning for Tamil handwritten character recognition using deep Siamese convolutional neural network. In: Mahmud, M., Kaiser, M.S., Kasabov, N., Iftekharuddin, K., Zhong, N. (eds.) AII 2021. CCIS, vol. 1435, pp. 204–215. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-82269-9_16
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Souibgui, M.A., Fornés, A., Kessentini, Y., Tudor, C.: A few-shot learning approach for historical ciphered manuscript recognition. In: ICPR (2021)
Stauffer, M., Fischer, A., Riesen, K.: Keyword spotting in historical handwritten documents based on graph matching. Pattern Recogn. 81, 240–253 (2018)
Sudholt, S., Fink, G.A.: PHOCNet: a deep convolutional neural network for word spotting in handwritten documents. In: ICFHR (2016)
Vinciarelli, A., Luettin, J.: A new normalization technique for cursive handwritten words. Pattern Recogn. Lett. 22, 1043–1050 (2001)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS (2016)
Wang, T., Xie, Z., Li, Z., Jin, L., Chen, X.: Radical aggregation network for few-shot offline handwritten Chinese character recognition. Pattern Recogn. Lett. 125, 821–827 (2019)
Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53, 1–34 (2020)
Wong, A., Yuille, A.L.: One shot learning via compositions of meaningful patches. In: ICCV (2015)
Acknowledgment
This work has been partially supported by the Spanish projects RTI2018-095645-B-C21, PID2021-126808OB-I00 and FCT-19-15244, and the Catalan projects 2017-SGR-1783, the CERCA Program/Generalitat de Catalunya, PhD Scholarship from AGAUR (2021FIB-10010), and the DIEM Graduate Research Scholarship entitled “Strumenti di supporto alla trascrizione di documenti manoscritti di interesse storico-culturale”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
De Gregorio, G. et al. (2022). A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts. In: Porwal, U., Fornés, A., Shafait, F. (eds) Frontiers in Handwriting Recognition. ICFHR 2022. Lecture Notes in Computer Science, vol 13639. Springer, Cham. https://doi.org/10.1007/978-3-031-21648-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-21648-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21647-3
Online ISBN: 978-3-031-21648-0
eBook Packages: Computer ScienceComputer Science (R0)