BLSTM-CTC Combination Strategies for Off-line Handwriting Recognition
Abstract
In this paper we present several combination strategies using multiple BLSTM-CTC systems. Given several feature sets our aim is to determine which strategies are the most relevant to improve on an isolated word recognition task (the WR2 task of the ICDAR 2009 competition), using a BLSTM-CTC architecture. We explore different combination levels: early integration (feature combination), mid level combination and late fusion (output combinations). Our results show that several combinations outperform single feature BLSTM-CTCs.