Biometric recognition using online uppercase handwritten text

摘要

This paper presents a handwritten text biometric recognition system suitable to be applied to short sequences of text (words). Strokes are considered the structural units of handwriting with words being regarded as two separate sequences: one of pen-down and one of pen-up strokes. Unsupervised categorization by means of a self-organized map allows mapping strokes to integers and the efficient comparison of the sequences by means of dynamic time warping. Measures obtained from each sequence are combined in a later step. This separation gives us the opportunity to show that pen-up strokes possess a surprisingly high discriminative power, while the performance of the combination suggests they may carry non-redundant information with respect to pen-down strokes.A writer identification rate of 92.38% and a minimum of detection cost function of 0.046 (4.6%) is achieved with 370 users and just one word. Results are improved up to 96.46% and 0.033 (3.3%) when combining two words.