Thai type style recognition
Chularat Tanprasert, Sutat Sae-Tang · 2003
Thai typed character recognition has been a very most popular research topic in Thailand. There are three commercial Thai OCR softwares available to the public at the present. But none of them can preserve the type styles of the original document image such as bold, italics, normal, and bold and italics styles into the output text file. This paper presents the technique for preserving the specified Thai type styles by applying a specific preprocessing with a supervised neural networks (NNs) learning algorithm. Experiments have been conducted and the results confirm that the proposed technique effectively preserves the type styles of Thai typed fonts from the original document image into the output text file.