ML Anthology

Text Identification in Complex Background Using SVM

Datong Chen, Hervé Bourlard, Jean-Philippe Thiran
CVPR 2001 pp. II:621-627
doi:10.1109/CVPR.2001.991021 /cvpr/2001/chen2001cvpr-text/

Abstract

This paper presents a fast and robust algorithm to identify text in image or video frames with complex backgrounds and compression effects. The algorithm first extracts the candidate text line on the basis of edge analysis, baseline location and heuristic constraints. Support Vector Machine (SVM) is then used to identify text line from the candidates in edge-based distance map feature space. Experiments based on large amount of images and video frames from different sources showed the advantages of this algorithm compared to conventional methods in both identification quality and computation time.

PDF CVPR Semantic Scholar

Cite

Text

Chen et al. "Text Identification in Complex Background Using SVM." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.991021

Markdown

[Chen et al. "Text Identification in Complex Background Using SVM." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/chen2001cvpr-text/) doi:10.1109/CVPR.2001.991021

BibTeX

@inproceedings{chen2001cvpr-text,
  title     = {{Text Identification in Complex Background Using SVM}},
  author    = {Chen, Datong and Bourlard, Hervé and Thiran, Jean-Philippe},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:621-627},
  doi       = {10.1109/CVPR.2001.991021},
  url       = {https://mlanthology.org/cvpr/2001/chen2001cvpr-text/}
}