Building a compact online MRF recognizer for large character set by structured dictionary representation and vector quantization technique
作者：
Highlights：
• We propose a method for building a compact online MRF recognizer.
• It is for large handwritten Japanese character set.
• It uses structured dictionary representation and VQ technique.
• The radical models are shared by different characters.
• Each character model is constructed from the constituent radical MRF models.
摘要
•We propose a method for building a compact online MRF recognizer.•It is for large handwritten Japanese character set.•It uses structured dictionary representation and VQ technique.•The radical models are shared by different characters.•Each character model is constructed from the constituent radical MRF models.
论文关键词：Online recognition,Compact recognizer,Structured dictionary,Vector quantization
论文评审过程：Available online 5 October 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.09.031
