← Back to papers
2017 NIPS NeurIPS 2017

Gated Recurrent Convolution Neural Network for OCR

Abstract

Optical Character Recognition (OCR) aims to recognize text in natural images. Inspired by a recently proposed model for general image classification, Recurrent Convolution Neural Network (RCNN), we propose a new architecture named Gated RCNN (GRCNN) for solving this problem. Its critical component, Gated Recurrent Convolution Layer (GRCL), is constructed by adding a gate to the Recurrent Convolution Layer (RCL), the critical component of RCNN. The gate controls the context modulation in RCL and balances the feed-forward information and the recurrent information. In addition, an efficient Bidirectional Long Short-Term Memory (BLSTM) is built for sequence modeling. The GRCNN is combined with BLSTM to recognize text in natural images. The entire GRCNN-BLSTM model can be trained end-to-end. Experiments show that the proposed model outperforms existing methods on several benchmark datasets including the IIIT-5K, Street View Text (SVT) and ICDAR.

🌉 Interdisciplinary Bridge — Computer Vision and Deep Learning
📈 Trend Setter — Document Analysis
🧭 Keyword Pioneer — gated recurrent convolution
🐣 Hot Topic Early Bird — sequence modeling
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Jianfeng Wang , Xiaolin Hu

Topics

Deep Learning > Architectures > Neural Networks Deep Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Learning Types > Representation Learning Deep Learning > Architectures > Recurrent Neural Networks Computer Vision > Applications > Document Analysis

Keywords

sequence modeling convolutional neural network recurrent neural network bidirectional lstm gated recurrent unit optical character recognition bidirectional long short-term memory gated recurrent convolution recurrent convolution neural network
Download PDF

Related papers

High-Order Attention Models for Visual Question Answering 2017
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization 2017
Premise Selection for Theorem Proving by Deep Graph Embedding 2017
Neural Program Meta-Induction 2017
Safe and Nested Subgame Solving for Imperfect-Information Games 2017