Abstract
The CROHME competitions have helped organize the field of handwritten mathematical expression recognition. This paper presents the evolution of the competition over its first 4 years, and its contributions to handwritten math recognition, and more generally structural pattern recognition research. The competition protocol, evaluation metrics and datasets are presented in detail. Participating systems are analyzed and compared in terms of the central mathematical expression recognition tasks: (1) symbol segmentation, (2) classification of individual symbols, (3) symbol relationships and (4) structural analysis (parsing). The competition led to the development of label graphs, which allow recognition results with conflicting segmentations to be directly compared and quantified using Hamming distances. We introduce structure confusion histograms that provide frequencies for incorrect subgraphs corresponding to ground-truth label subgraphs of a given size and present structure confusion histograms for symbol bigrams (two symbols with a relationship) for CROHME 2014 systems. We provide a novel analysis combining results from competing systems at the level of individual strokes and stroke pairs; this virtual merging of system outputs allows us to more closely examine limitations for current state-of-the-art systems. Datasets along with evaluation and visualization tools produced for the competition are publicly available.
Similar content being viewed by others
Notes
A well-written history of mathematical notation is available [11].
The MathML \(\texttt {<mrow>}\) element is used to group sub-expressions, which usually contain one or more operators with their respective operands. This element renders as a horizontal row containing its arguments.
The first example of such a grammar for math recognition was presented by Chou in the late 1980s [47].
References
Anderson, R.H.: Syntax-directed recognition of hand-printed two-dimensional mathematics. In: Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc., Symposium, pp. 436–459. ACM, New York, NY, USA (1967)
Mouchère, H., Viard-Gaudin, C., Kim, D.H., Kim, J.H., Utpal, G.: Crohme 2011: competition on recognition of online handwritten mathematical expressions. In: Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR). Beijing, China (2011)
Mouchère, H., Viard-Gaudin, C., Kim, D.H., Kim, J.H., Utpal, G.: Icfhr 2012—competition on recognition of on-line mathematical expressions (crohme 2012). In: Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition (ICFHR). Bari, Italy (2012)
Mouchère, H., Viard-Gaudin, C., Zanibbi, R., Garain, U., Kim, D.H., Kim, J.H.: Icdar 2013 crohme: third international competition on recognition of online handwritten mathematical expressions. In: Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR). Washington, DC, USA (August 2013)
Mouchère, H., Viard-Gaudin, C., Zanibbi, R., Utpal, G.: Icfhr 2014—competition on recognition of on-line mathematical expressions (crohme 2014). In: Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR). Creta, Greece (2014)
Chan, K., Yeung, D.: Mathematical expression recognition: a survey. Int. J. Doc. Anal. Recognit. 3(1), 3–15 (2000)
Sain, K., Dasgupta, A., Garain, U.: Emers: a tree matching-based performance evaluation of mathematical expression recognition systems. Int. J. Doc. Anal. Recognit. 14(1), 75–85 (2011)
Zanibbi, R., Mouchère, H., Viard-Gaudin, C.: Evaluating structural pattern recognition for handwritten math via primitive label graphs. In: IS&T/SPIE Electronic Imaging, pp. 865817-1–865817-11. International Society for Optics and Photonics (2013)
Blostein, D., Grbavec, A.: Recognition of mathematical notation. In: Bunke, H., Wang, P. (eds.) Handbook of Character Recognition and Document Image Analysis, pp. 557–582. World Scientific Publishing Company (1997)
Zanibbi, R., Blostein, D.: Recognition and retrieval of mathematical expressions. Int. Doc. Anal. Recognit. 15(4), 331–357 (2012)
Cajori, F.: A History of Mathematical Notations, vol. 2. The Open Court Publishing Company, Chicago (1929)
Marriott, K., Meyer, B., Wittenburg, K.B.: Visual language theory, ch. In: A Survey of Visual Language Specification and Recognition, pp. 5–85. Springer, New York (1998)
Awal, A.-M., Mouchère, H., Viard-Gaudin, C.: Towards handwritten mathematical expression recognition. In: Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR), pp. 1046–1050 (2009)
Quiniou, S., Mouchère, H., Saldarriaga, S., Viard-Gaudin, C., Morin, E., Petitrenaud, S., Medjkoune, S.: Hamex—a handwritten and audio dataset of mathematical expressions. In: Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR), pp. 452–456 (2011)
Stria, J., Bresler, M., Průs̆a, D., Hlavc, V.: Mfrdb: Database of annotated on-line mathematical formulae. In: Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 542–547 (2012)
Aguilar, F.D.J., Hirata, N.S.: Expressmatch: a system for creating ground-truthed datasets of online mathematical expressions. In: Proceedings of 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 155–159. IEEE (2012)
MacLean, S., Labahn, G., Lank, E., Marzouk, M., Tausky, D.: Grammar-based techniques for creating ground-truthed sketch corpora. Int. J. Doc. Anal. Recognit. 14(1), 65–74 (2011)
Garain, U., Chaudhuri, B.B.: A corpus for OCR research on mathematical expressions. Int. J. Doc. Anal. Recognit. 7(4), 241–259 (2005)
Zanibbi, R., Pillay, A., Mouchère, H., Viard-Gaudin, C., Blostein, D.: Stroke-based performance metrics for handwritten mathematical expressions. In: Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR), pp. 334–338. IEEE (2011)
Álvaro, F., Sánchez, J.-A., Benedí, J.-M.: An image-based measure for evaluation of mathematical expression recognition. In: Sanches, J., Micó, L., Cardoso J. (eds.) Pattern Recognition and Image Analysis, vol. 7887 of Lecture Notes in Computer Science, pp. 682–690. Springer, Berlin (2013)
Garain, U., Chaudhuri, B.: OCR of Printed Mathematical Expressions. Springer, New York (2007). doi:10.1007/978-1-84628-726-8_11
Tapia, E., Rojas, R.: A survey on recognition of on-line handwritten mathematical notation. In: Technical Report, Free University of Berlin, January (2007)
Blostein, D., Zanibbi, R.: Processing mathematical notation, chap. 5.6. In: Doermann, D., Tombre, K. (eds.) Handbook of Document Image Processing and Recognition. Springer, London (2014)
Simistira, F., Katsouros, V., Carayannis, G.: A template matching distance for recognition of on-line mathematical symbols. In: Proceedings of the 11th International Conference on Frontiers in Handwriting Recognition (ICFHR), (Montréal), pp. 415–420 (2008)
Stria, J., Průs̆a, D.: Web application for recognition of mathematical formulas. In: Proc. Conf. Theory and Practice of Information Technologies, (Vrátna dolina, Slovak Republic), pp. 47–54 (2011)
Stria, J., Bresler, M., Průs̆a, D., Hlavác, V.: Mfrdb: Database of annotated on-line mathematical formulae. In: Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 542–547 (2012)
Awal, A.-M., Mouchère, H., Viard-Gaudin, C.: Improving online handwritten mathematical expressions recognition with contextual modeling. In: Proceedings of the 12th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 427–432 (2010)
Awal, A.-M., Mouchère, H., Viard-Gaudin, C.: A global learning approach for an online handwritten mathematical expression recognition system. Pattern Recognit. Lett. 35(1), 68–77 (2014). Frontiers in Handwriting Processing
Hu, L., Zanibbi, R.: HMM-based recognition of online handwritten mathematical symbols using segmental k-means initialization and a modified pen-up/down feature. In: Proceedings of International Conference Document Analysis and Recognition, pp. 457–462. Beijing, China (Sept. 2011)
Hu, L., Hart, K., Pospesel, R., Zanibbi, R.: Baseline extraction-driven parsing of handwritten mathematical expressions. In: Proceedings of International Conference Pattern Recognition, pp. 326–330. Tsukuba Science City, Japan (Nov. 2012)
Hu, L., Zanibbi, R.: Segmenting handwritten math symbols using AdaBoost and multi-scale shape context features. In: Proceedings of International Conference Document Analysis and Recognition, pp. 1180–1184. Washington, USA (2013)
Eto, Y., Suzuki, M.: Mathematical formula recognition using virtual link network. In: Proceeding of International Conference Document Analysis and Recognition, pp. 762–767. Seattle, USA (2001)
Davila, K., Ludi, S., Zanibbi, R.: Using off-line features and synthetic data for on-line handwritten math symbol recognition. In: Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 323–328. Crete, Greece (2014)
Zanibbi, R., Blostein, D., Cordy, J.R.: Recognizing mathematical expressions using tree transformation. IEEE Tran. Pattern Anal. Mach. Intel. 24(11), 1455–1467 (2002)
Álvaro, F., Zanibbi, R.: A shape-based layout descriptor for classifying spatial relationships in handwritten math. In: ACM Symposium Document Engineering, pp. 123–126. Florence, Italy (2013)
Liwicki, M., Bunke, H.: Feature selection for HMM and BLSTM based handwriting recognition of whiteboard notes. Int. J. Pattern Recognit. Artif. Intell. 23(5), 907–923 (2009)
Celik, M., Yanikoglu, B.: Mathematical formula recognition using a 2D stochastic graph grammar. In: Proceedings of International Conference Document Analysis and Recognition, pp. 161–166. Beijing, China (2011)
Julca-Aguilar, F., Hirata, N., Viard-Gaudin, C., Mouchère, H., Medjkoune, S.: Mathematical symbol hypothesis recognition with rejection option. In: Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 500–504. Crete, Greece (2014)
Le, D., Phan, T.V., Nakagawa, M.: A system for recognizing online handwritten mathematical expressions and improvement of structural analysis. In: Proceedings of 11th IAPR International Workshop on Document Analysis Systems (DAS). Tours, France (2014)
Zhu, B., Gao, J., Nakagawa, M.: Objection function design for MCE-based combination of on-line and off-line character recognizers for on-line handwritten Japanese text recognition. In: Proceedings of the 11th International Conference on Document Analysis and Recognition (ICDAR), pp. 594–599. Beijing, China (2011)
Lee, A., Nakagawa, M.: A tool for ground-truthing online handwritten mathematical expressions. In: International Graphonomics Society Conference. Nara, Japan (2013)
Álvaro, F., Sánchez, J., Benedí, J.: Recognition of printed mathematical expression using two-dimensional stochastic context-free grammars. In: Proceedings of International Conference Document Analysis and Recognition, pp. 1225–1229. Beijing, China (2011)
Álvaro, F., Sánchez, J., Benedí, J.: Recognition of online handwritten mathematical expressions using 2D stochastic context-free grammars and Hidden Markov Models. Pattern Recognit. Lett. 35, 56–67 (2014)
Álvaro, F., Sánchez, J., Benedí, J.: Offline features for classifying handwritten math symbols with recurrent neural networks. In: Proceedings of International Conference Pattern Recognition, p. (to appear) (2014)
Labahn, G., Lank, E., MacLean, S., Marzouk, M. S., Tausky, D.: Mathbrush: a system for doing math on pen-based devices. In: Proceedings of Document Analysis Systems, pp. 599–606. Nara, Japan (2008)
MacLean, S., Labahn, G.: A new approach for recognizing handwritten mathematics using relational grammars and fuzzy sets. Int. J. Doc. Anal. Recognit. 16(2), 139–163 (2013)
Chou, P.A.C.: Recognition of equations using a two-dimensional stochastic context-free grammar. In: Pearlman, W.A. (ed.) Visual Communications and Image Processing IV, vol. 1199 of SPIE Proceedings Series, pp. 852–863 (1989)
Zanibbi, R., Blostein, D., Cordy, J.R.: Recognizing mathematical expressions using tree transformation. Pattern Analysis and Machine Intelligence, IEEE Transactions on 24, 1455–1467 (2002)
Acknowledgments
We thank Drs. Kim and Kim (KAIST, South Korea), for their help during the first CROHME. Part of this research was supported by the National Science Foundation (USA) Grant No. IIS-1016815.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mouchère, H., Zanibbi, R., Garain, U. et al. Advancing the state of the art for handwritten math recognition: the CROHME competitions, 2011–2014. IJDAR 19, 173–189 (2016). https://doi.org/10.1007/s10032-016-0263-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-016-0263-5