Recognition of handprinted Hebrew characters using features selected in the Hough transform space

https://doi.org/10.1016/0031-3203(85)90033-0Get rights and content

Abstract

Automatic identification of handprinted Hebrew characters is described in this paper. The recognition model devised constitutes a multi-stage system. In the first stage a coarse classifier allocates the input patterns into one of 17 categories, based on the number and the location of end points within predetermined regions in the characters matrix. The second stage uses features extracted in the Hough transform space to classify characters assigned to each of 16 categories. The remaining one category, composed of similar, square-like (rotated L shape) classes, is recognized by structural analysis and a statistical classifier. An additional step of postprocessing is added to compensate for the sensitivity of the Hough transform to the existence of similar classes within some of the categories. Experiments were conducted with a multi-author (40 writers) data base. An average recognition rate of 86.9% was observed for the system. This compared favorably with the results of two other recognition methods.

References (22)

  • H.C. Andrews

    Multidimensional rotations in feature selection

    IEEE Trans. Comput. C-20

    (1971)
  • Cited by (0)

    View full text