Handwritten Chinese character recognition using displacement extraction based on directional features
This paper presents a recognition method for handwritten Chinese characters using displacement extraction based on directional features. In the proposed method, after extracting the features from an input image, the displacement is extracted by the minimization of an energy functional, which consists of the Euclidean distance and the smoothness of the extracted displacement. Experiments are performed on a set of handwritten Chinese characters (ETL-8B). The improvement of the recognition performance of the proposed method is achieved as compared with the method without the displacement extraction.
Unable to display preview. Download preview PDF.
- Saito, T., Yamada, H. and Yamamoto, K.: An analysis of handprinted Chinese characters by directional pattern matching approach. Trans. IECE (Japan), J65-D (1982) 550–557, in JapaneseGoogle Scholar
- Jain, A. K. and Chandrasekaran, B.: Dimensionality and sample size considerations in pattern recognition practice. Handbook of Statistics, Krishnaiah, P. R. and Kanal, L. N., eds, 2 (1982), North-Holland, AmsterdamGoogle Scholar