Abstract
This paper compares a number of different statistical and syntactic recognition methods on a difficult off-line OCR dataset. The motivation for such a test is to show that syntactic methods can perform as robustly as purely statistical techniques on noisy data. The main result is that, even given a very simplistic and idiosyncratic input coding, the syntactic method performs slightly better than any of the other methods. Furthermore, it is likely that the syntactic method could significantly outperform the other methods given a less idiosyncratic input coding.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
I. Aleksander, “Wisard — a radical step forward in image recognition,” Sensor Review, vol. July, pp. 120–124, (1984).
K. Yamamoto and S. Mori, “Recognition of hand-printed characters by an outermost point method,” Pattern Recognition, vol. 12, pp. 229–236, (1980).
R. Tregidgio, “Parallel implementation of statistical classifiers for optical character recognition,” PhD Thesis, University of Essex, (1992).
D.Angluin, C.H.Smith: ”Inductive Inference: Theory and Methods”. Computing Surveys, Vol. 15, N 3, 1983.
H.Rulot, E.Vidal: ”Modelling (Sub)string-Length-Based Constraints through a Grammatical Inference Method”. In “Patter Recognition: Theory and Applications”. Eds: Devijver and Kittler, pp. 451–459, Springer Verlag, 1987.
F.Torro, E.Vidal, H.Rulot: ”Fast and Accurate Speaker Independent Speech Recognition Using Structurals Models Learnt by the ECGI”, in “Signal Processing V: Theories and Applications”. L.Torres, E.Masgrav, M.A.Lagunas (Eds.). Elsevier Science Pub., 1990.
E.Vidal, H.Rulot, J.M.Valiente, G.Andreu: ”Font Independent Mixed-Size Digit Recognition Through Error-Correcting Grammatical Inference (ECGI)”. ICPR-Proc., La Hague, pp.334–337, 1992.
E.Vidal, H.Rulot, J.M.Valiente and G.Andreu: ”Recognition of Planar Shapes Through the Error-Correcting Grammatical Inference Algorithm (ECGI)”, First Int. Colloquium on Grammatical Inference: Theory, Applications and Alternatives, Proc. University of Essex, April 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lucas, S., Vidal, E., Amiri, A., Hanlon, S., Amengual, J.C. (1994). A comparison of syntactic and statistical techniques for off-line OCR. In: Carrasco, R.C., Oncina, J. (eds) Grammatical Inference and Applications. ICGI 1994. Lecture Notes in Computer Science, vol 862. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58473-0_146
Download citation
DOI: https://doi.org/10.1007/3-540-58473-0_146
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58473-5
Online ISBN: 978-3-540-48985-6
eBook Packages: Springer Book Archive