Visualization of Extracted Digital Ink Text Based on Reliability

The result of segmented digital ink text contains three levels: characters, lines and paragraphs. Characters make up a significant percentage in the result and the situations of them are always complex. Automatic methods hardly provide completely correct result of extracted characters. So the result needs to be modified by human-computer interactive operation. Optimized visualization could improve the efficiency of modification. Therefore oriented to the modification of the errors of extracted characters, according to the adjacent and overlapping among characters, the paper proposes an improved way of visualization. The approach firstly makes assessment of extracted characters and then visualized them based on diffident reliability of correction. Testing on many sorts of extracted characters from digital ink text in Chinese, the approach is effective.