Line-Members - a Novel Feature in On-Line Whiteboard Note Recognition
Joachim Schenk, Janis Lenz, Gerhard Rigoll · 2008
Confusion-matrices show that character mix-ups between similar looking letters differing in size rather than in shape (like “s ” and “S ” or “e ” and “l”), as well as between tall letters (such as “M ” and “t”) and small case letters (such as “s ” and “a”) and vice versa can occur in on-line whiteboard note recognition. This paper introduces a novel feature called “line-member” feature that adds discriminance to the feature vector. Thereby, for certain sample points the script line as-sociation is estimated using the Viterbi algorithm and taken as a feature. As our experiments indicate, a relative improve-ment of r = 3.3 % in character level and r = 3.4 % in word level accuracy compared to a baseline sys-tem without the novel “line-member ” feature can be achieved. In addition, the character confusion as de-scribed above can be reduced.