Extraction and Optimization of B-Spline PBD Templates for Recognition of Connected Handwritten Digit Strings

@article{Lu2002ExtractionAO,
  title={Extraction and Optimization of B-Spline PBD Templates for Recognition of Connected Handwritten Digit Strings},
  author={Zhongkang Lu and Zheru Chi and Wan-Chi Siu},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  year={2002},
  volume={24},
  pages={132-139}
}
Recognition of connected handwritten digit strings is a challenging task due mainly to two problems: poor character segmentation and unreliable isolated character recognition. In this paper, we first present a rational B-spline representation of digit templates based on Pixel-to-Boundary Distance (PBD) maps. We then present a neural network approach to extract B-spline PBD templates and an evolutionary algorithm to optimize these templates. In total, 1,000 templates (100 templates for each of… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

Prototype Optimization of a Nearest Neighbor Classifier Using a Multi-Layer Neural Network

  • H. Yan
  • Pattern Recognition, vol. 26, pp. 317-324, .
  • 1993
Highly Influential
7 Excerpts

A Background-Thinning Based Algorithm for Separating Handwritten Touching Digit Strings

  • Z. K. Lu, Z. Chi, W. C. Siu, P. F. Shi
  • Pattern Recognition, vol. 32, no. 6, pp. 921-933…
  • 1999
2 Excerpts

Similar Papers

Loading similar papers…