SPATIAL-TEMPORAL ARTIFICIAL NEURONS APPLIED TO ONLINE CURSIVE HANDWRITTEN CHARACTER RECOGNITION

摘要

In this paper we present our latest experiments on the utilization of the recently developed Spatio-Tempora! Artificial Neuron (STAN). This neuron has the capability to process asynchronous (continuous) spatio-temporal data sequences and compare them with the help of Hermitian distance. The problem addressed is that of online cursive (non-isolated) handwritten character recognition. We develop a system based on three modules: pre-processing, feature detection and character classification. The results obtained are encouraging and we also suggest further avenues of improvement in the system.