Exploiting Ruling Line Artifacts in Writer Identification
Jin Chen, Daniel Lopresti · 2015
In this paper, we address the writer identification problem for noisy handwritten documents written on a substrate of pre-printed ruling lines. Instead of attempt-ing to remove rulings and to recover broken strokes, we incorporate rulings to help with the identification task through the use of new displacement features. Experi-ments involving 61 writers and 4,890 handwritten text lines show that our technique is effective, with a rel-ative 10 % performance gain over the baseline system which attempts to remove ruling lines and recover bro-ken strokes. 1.