NEURAL NETWORK­BASED CONTEXT DRIVEN RECOGNITION OF ON­LINE CURSIVE SCRIP

Most of the state­of­the­art systems for cursive script recognition are based on a combination of neural networks (NN) and hidden Markov models (HMMs) 1;2 . The post­processing stage is almost exclusively modeled using HMMs and the dynamic programming (DP) technique (the Viterbi algorithm) is used to efficiently search the space of possible segmentations. In this work we introduce a neural network­based model for representing handwritten patterns as an alternative to HMMs. In addition, we present a new algorithm that uses context information to segment, modify and organize bottom up information in order to achieve successful recognition.