The Use of Dynamic Writing Information in a Connectionist On-line Cursive Handwriting Recognition System

Abstract

In this paper we present NPen++, a connectionist system for writer independent, large vocabulary on-line cursive handwriting recognition. This system combines a robust input representation, which preserves the dynamic writing information, with a neural network architecture, a so called Multi-State Time Delay Neural Network (MS-TDNN), which integrates recognition and segmentation in a single framework. Our preprocessing transforms the original coordinate sequence into a (still temporal) sequence of feature vectors, which combine strictly local features, like curvature or writing direction, with a bitmap-like representation of the coordinate's proximity. The MS-TDNN architecture is well suited for handling temporal sequences as provided by this input representation. Our system is tested both on writer dependent and writer independent tasks with vocabulary sizes ranging from 400 up to 20,000 words. For example, on a 20,000 word vocabulary we achieve word recognition rates up to 88.9% (writer dependent) and 84.1% (writer independent) without using any language models.