An Image-Based Measure for Evaluation of Mathematical Expression Recognition
Mathematical expression recognition is an active research field that is related to document image analysis and typesetting. In this study, we present a novel global performance evaluation measure for mathematical expression recognition based on image matching. Using an image representation for evaluation tries to overcome the representation ambiguity as human beings do. The results of a recent competition were used to perform several experiments in order to analyze the benefits and drawbacks of this measure.
KeywordsPerformance evaluation Image-based modeling Mathematical expression recognition
Unable to display preview. Download preview PDF.
- 1.Álvaro, F., Sánchez, J.A., Benedí, J.M.: Unbiased evaluation of handwritten mathematical expression recognition. In: Proceedings of ICFHR, Italy, pp. 181–186 (2012)Google Scholar
- 3.Chou, P.A.: Recognition of equations using a two-dimensional stochastic context-free grammar. In: Pearlman, W.A. (ed.) Visual Communications and Image Processing IV. SPIE Proceedings Series, vol. 1199, pp. 852–863 (1989)Google Scholar
- 6.Mouchére, H., Viard-Gaudin, C., Garain, U., Kim, D.H., Kim, J.H.: ICFHR 2012 – Competition on Recognition of On-line Mathematical Expressions (CROHME 2012). In: Proceedings of ICFHR, Italy, pp. 807–812 (2012)Google Scholar
- 8.Sain, K., Dasgupta, A., Garain, U.: EMERS: a tree matching-based performance evaluation of mathematical expression recognition system. International Journal of Document Analysis and Recognition (2010)Google Scholar
- 9.Toselli, A.H., Juan, A., Vidal, E.: Spontaneous Handwriting Recognition and Classification. In: Proceedings of ICPR, England, UK, pp. 433–436 (2004)Google Scholar
- 11.Zanibbi, R., Pillay, A., Mouchere, H., Viard-Gaudin, C., Blostein, D.: Stroke-based performance metrics for handwritten mathematical expressions. In: Proceedings of ICDAR, pp. 334–338 (2011)Google Scholar