Handwritten Digit Segmentation in Images of Historical Documents with One-Class Classifiers

@article{Alves2008HandwrittenDS,
  title={Handwritten Digit Segmentation in Images of Historical Documents with One-Class Classifiers},
  author={V. M. O. Alves and Adriano Lorena In{\'a}cio de Oliveira and E. R. Silva and Carlos A. B. Mello},
  journal={2008 20th IEEE International Conference on Tools with Artificial Intelligence},
  year={2008},
  volume={2},
  pages={41-44}
}
A novel method is proposed herein for handwritten digit segmentation in historical document images. It is based on one-class classifiers, which are used to distinguish isolated characters from touching characters. In contrast to other techniques based on feed forward neural networks, the proposed method does not require negative data in the training phase. Three methods for feature extraction and five one class classifiers are considered and have their performance compared. Experimental results… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

Real-time numeric character recognition system based on finger movements

  • 2013 International Conference on Electrical Information and Communication Technology (EICT)
  • 2014
VIEW 1 EXCERPT
CITES BACKGROUND

A real time numeric character recognition system using artificial neural network

  • 2013 2nd International Conference on Advances in Electrical Engineering (ICAEE)
  • 2013
VIEW 1 EXCERPT
CITES BACKGROUND

An improved method for 7-segment numeric character recognition

  • 2013 International Conference on Informatics, Electronics and Vision (ICIEV)
  • 2013
VIEW 1 EXCERPT
CITES BACKGROUND

Class-Dependent Locality Preserving Projections for Multimodal Scenarios

  • 2012 IEEE 24th International Conference on Tools with Artificial Intelligence
  • 2012
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

NIST Form-Based Handprint Recognition System

Gerald T Candela, Darrin L Dimmick, +3 authors C Wilson
  • 1994
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

An Efficient Grey-Level Thresholding Algorithm for Historic Document Imagens

Mello, B C.A.
  • Journal of Cultural Heritage,
  • 2008
VIEW 2 EXCERPTS

Handwritten numeral string recognition using neural network classifier trained with negative data

  • Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition
  • 2002
VIEW 3 EXCERPTS