On using entropy for enhancing handwriting preprocessing

Abstract

Handwriting is an important modality for Human-Computer Interaction. For medical professionals, handwriting is (still) the preferred natural method of documentation. Handwriting recognition has long been a primary research area in Computer Science. With the tremendous ubiquity of smartphones, along with the renaissance of the stylus, handwriting recognition has become a new impetus. However, recognition rates are still not 100% perfect, and researchers still are constantly improving handwriting algorithms. In this paper we evaluate the performance of entropy based slant- and skew-correction, and compare the results to other methods. We selected 3700 words of 23 writers out of the Unipen-ICROW-03 benchmark set, which we annotated with their associated error angles by hand. Our results show that the entropy-based slant correction method outperforms a window based approach with an average precision of ±6:02° for the entropy-based method, compared with the ±7:85° for the alternative. On the other hand, the entropy-based skew correction yields a lower average precision of ±2:86°, compared with the average precision of ±2:13° for the alternative LSM based approach. © 2012 by the authors; licensee MDPI, Basel, Switzerland.