Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior

Donaldson, Katherine; Myers, Gregory K.

doi:10.1109/CVPR.2005.87

Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior

Katherine Donaldson, Gregory K. Myers

CVPR 2005 pp. 1188-1195

doi:10.1109/CVPR.2005.87 /cvpr/2005/donaldson2005cvpr-bayesian/

Abstract

To increase the range of sizes of video scene text recognizable by optical character recognition (OCR), we developed a Bayesian super-resolution algorithm that uses a text-specific bimodal prior. We evaluated the effectiveness of the bimodal prior, compared with and in conjunction with a piecewise smoothness prior, visually and by measuring the accuracy of the OCR results on the variously super-resolved images. The bimodal prior improved the readability of 4- to 7-pixel-high scene text significantly better than bicubic interpolation, and increased the accuracy of OCR results better than the piecewise smoothness prior.

CVPR Semantic Scholar

Cite

Text

Donaldson and Myers. "Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.87

Markdown

[Donaldson and Myers. "Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/donaldson2005cvpr-bayesian/) doi:10.1109/CVPR.2005.87

BibTeX

@inproceedings{donaldson2005cvpr-bayesian,
  title     = {{Bayesian Super-Resolution of Text in Video with a Text-Specific Bimodal Prior}},
  author    = {Donaldson, Katherine and Myers, Gregory K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {1188-1195},
  doi       = {10.1109/CVPR.2005.87},
  url       = {https://mlanthology.org/cvpr/2005/donaldson2005cvpr-bayesian/}
}