The generalized Hough transform is a useful method for detecting arbitrary 2-dimensional shapes. Based on the consideration that handwritten Chinese characters are complex 2-dimensional shapes, we make an attempt to recognize them by using the generalized Hough transform. Features extracted from the parameter space are used to calculate the similarity measure between two character images. The algorithm is implemented in a look-up-table scheme which can be extended to other applications of pattern recognition. Experimental results on personal (writer-dependent) handwritten Chinese character recognition show that this algorithm is suitable for the pre-classification of personal handwritten Chinese character recognition.
A personal handwritten Chinese character recognition algorithm based on the generalized Hough transform
Proceedings of 3rd International Conference on Document Analysis and Recognition ; 2 ; 828-831 vol.2
01.01.1995
391932 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 1995
|Generalized Hough Transform for Arabic Optical Character Recognition
British Library Conference Proceedings | 2003
|The Field Transform and Its Application to Personal Handwritten Chinese Character Recognition
British Library Conference Proceedings | 1995
|