Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory

Abstract

Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging recent memory accessing mechanisms in MANNs, our architecture demonstrates superior performance against other CRNN counterparts in three real-world long text OCR datasets.

References in corpus (5)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• On the difficulty of training Recurrent Neural Networks
• Rosetta: Large scale system for text detection and recognition in images
• Reading Scene Text with Attention Convolutional Sequence Modeling
• Memory Augmented Neural Networks with Wormhole Connections