Text and non-text recognition using modified HOG descriptor

@article{Sah2017TextAN,
  title={Text and non-text recognition using modified HOG descriptor},
  author={Ankit Kumar Sah and Showmik Bhowmik and Samir Malakar and Ram Sarkar and Ergina Kavallieratou and Nikos Vasilopoulos},
  journal={2017 IEEE Calcutta Conference (CALCON)},
  year={2017},
  pages={64-68}
}
In order to convert a document image in its editable version, an OCR engine must identify and separate the nontext regions from text regions of a given document image. In the present work, a technique is developed to classify various text and non-text regions present in a document image. For that purpose, a modified version of Histogram of Oriented Gradient (HOG) is used as a feature descriptor. Multi-Layer Perceptron (MLP) is chosen from a pool of classifier by comparing the recognition… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Handwritten Bangla Word Recognition Using HOG Descriptor

  • 2014 Fourth International Conference of Emerging Applications of Information Technology
  • 2014
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A texture-based method for document segmentation and classification

  • South African Computer Journal
  • 2006
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Statistical Genomics: Methods and Protocols

T. C. Smith, E. Frank
  • chapter Introducing Machine Learning Concepts with WEKA, pages 353378. Springer, New York, NY
  • 2016
VIEW 1 EXCERPT

Text and non-text segmentation based on connected component features

  • 2015 13th International Conference on Document Analysis and Recognition (ICDAR)
  • 2015
VIEW 1 EXCERPT

Suppression of non-text components in handwritten document images

  • 2011 International Conference on Image Information Processing
  • 2011
VIEW 2 EXCERPTS

Similar Papers

Loading similar papers…