Character Recognition by Adaptive Statistical Similarity

Thomas Breuel
International Conference for Document Analysis and Recognition (ICDAR), IEEE Computer Society, 2003
accepted for publication


Abstract:

Handwriting recognition and OCR systems need to cope with a wide variety of writing styles and fonts, many of them possibly not previously encountered during training. This paper describes a notion of Bayesian sta- tistical similarity and demonstrates how it can be applied to rapid adaptation to new styles. The ability to general- ize across different problem instances is illustrated in the Gaussian case, and the use of statistical similarity Gaus- sian case is shown to be related to adaptive metric classi- fication methods. The relationship to prior approaches to multitask learning, as well as variable or adaptive metric classification, and hierarchical Bayesian methods, are dis- cussed. Experimental results on character recognition from the NIST3 database are presented.

Files:

  CharRecAdapStatSim.pdf

BibTex:

@inproceedings{ BREU2003,
	Title = {Character Recognition by Adaptive Statistical Similarity},
	Author = {Thomas Breuel},
	BookTitle = {International Conference for Document Analysis and Recognition (ICDAR)},
	Note = {accepted for publication},
	Year = {2003},
	Publisher = {IEEE Computer Society}
}

     
Last modified:: 30.08.2016