2015
DOI: 10.1117/12.2076119 View full text |Buy / Rent full text
|
|

Abstract: Historical Chinese character recognition is very important to larger scale historical document digitalization, but is a very challenging problem due to lack of labeled training samples. This paper proposes a novel nonlinear transfer learning method, namely Gaussian Process Style Transfer Mapping (GP-STM). The GP-STM extends traditional linear Style Transfer Mapping (STM) by using Gaussian process and kernel methods. With GP-STM, existing printed Chinese character samples are used to help the recognition of his… Show more

Help me understand this report

Search citation statements

Order By: Relevance
Select...
0
2
0

Publication Types

Select...

Relationship

0
0

Authors

Journals