The neural-based segmentation of cursive words using enhanced heuristics

@article{Cheng2005TheNS,
  title={The neural-based segmentation of cursive words using enhanced heuristics},
  author={Chun Ki Cheng and Michael Blumenstein},
  journal={Eighth International Conference on Document Analysis and Recognition (ICDAR'05)},
  year={2005},
  pages={650-654 Vol. 2}
}
This paper presents an enhanced heuristic segmenter (EHS) and an improved neural-based segmentation technique for segmenting cursive words and validating prospective segmentation points respectively. The EHS employs two new features, ligature detection and a neural assistant, to locate prospective segmentation points. The improved neural-based segmentation technique can then be used to examine the prospective segmentation points by fusion of confidence values obtained from left and centre… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 16 CITATIONS

Off-line cursive script recognition: current advances, comparisons and remaining problems

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Performance Comparison between Contour-Based and Enhanced Heuristic-Based for Character Segmentation

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Over-segmentation of handwriting Arabic scripts using an efficient heuristic technique

  • Husam Al Hamad
  • 2012 International Conference on Wavelet Analysis and Pattern Recognition
  • 2012
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Handwritten Text Segmentation Using Pixel Based Approach

VIEW 1 EXCERPT

A knowledge-based recognition system for historical Mongolian documents

VIEW 1 EXCERPT
CITES BACKGROUND

Neural network based over-segmentation for scene text recognition

VIEW 1 EXCERPT
CITES METHODS

Detecting Main Body Size in Document Images

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

Use an efficient neural network to improve the Arabic handwriting recognition

  • Husam Ahmed Al Hamad
  • Computer Science
  • 2013 IEEE International Conference on Signal and Image Processing Applications
  • 2013

Neural networks for document image preprocessing: state of the art

VIEW 2 EXCERPTS
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

A new segmentation algorithm for handwritten word recognition

VIEW 4 EXCERPTS

A modified direction feature for cursive character recognition

VIEW 3 EXCERPTS

Basli, “A novel feature extraction technique for the recognition of segmented handwritten characters

  • M. Blumenstein, H. B. Verma
  • Proceedings of the Seventh International Conference on Document Analysis and Recognition,
  • 2003

Analysis of segmentation performance on the CEDAR benchmark database

VIEW 1 EXCERPT

A Simple and Effective Cursive Word Segmentation Method

  • G. Nicchiotti, C. Scagliola
  • Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition,
  • 2000
VIEW 1 EXCERPT

Knowledge-based English cursive script segmentation

VIEW 1 EXCERPT