A HMM Toolkit (HTK) and Combination of Multiple Classifiers for Recognition Offline Handwritten Arabic Words

@inproceedings{Maqqor2015AHT,
  title={A HMM Toolkit (HTK) and Combination of Multiple Classifiers for Recognition Offline Handwritten Arabic Words},
  author={Ahlam Maqqor and Akram Halli and Khaled Satori and Hamid Tairi and Ben Abdellah},
  year={2015}
}
The paper proposed approach introduces a methodology based on combining methods of decision fusion and using the HMM-Toolkit (HTK) for a rapid implementation of our designed recognition system. First, a pre-processing phase is done to prepare the image of the introduced text .The obtained images are then used for features extraction with Sliding window technique along the line image. The sequence of features vectors is represented in four stream’s group: 1) Density values of pixels concatenated… CONTINUE READING

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Using HMM Toolkit (HTK) for recognition of arabic manuscripts characters

  • 2014 International Conference on Multimedia Computing and Systems (ICMCS)
  • 2014
VIEW 1 EXCERPT

Using HMM based recognizers for writer identification and verification

  • Ninth International Workshop on Frontiers in Handwriting Recognition
  • 2004
VIEW 1 EXCERPT

Pattern Recognition, Second Edition. Copyright 2003, Elsevier(USA)

S. Theodoridis, K.Koutroumbs
  • 2003
VIEW 1 EXCERPT

Off-Line Arabic Character Recognition – A Review

  • Pattern Analysis & Applications
  • 2002
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…