Recursive Recurrent Nets with Attention Modeling for OCR in the Wild

We present recursive recurrent neural networks with attention modeling (R2AM) for lexicon-free optical character recognition in natural scene images. The primary advantages of the proposed method are: (1) use of recursive convolutional neural networks (CNNs), which allow for parametrically efficient...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2231 - 2239
Main Authors Chen-Yu Lee, Osindero, Simon
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2016
Subjects
Character recognition
Computational modeling
Feature extraction
Optical character recognition software
Predictive models
Recurrent neural networks
Text recognition
Online AccessGet full text

Cover

More Information
Summary:We present recursive recurrent neural networks with attention modeling (R2AM) for lexicon-free optical character recognition in natural scene images. The primary advantages of the proposed method are: (1) use of recursive convolutional neural networks (CNNs), which allow for parametrically efficient and effective image feature extraction, (2) an implicitly learned character-level language model, embodied in a recurrent neural network which avoids the need to use N-grams, and (3) the use of a soft-attention mechanism, allowing the model to selectively exploit image features in a coordinated way, and allowing for end-to-end training within a standard backpropagation framework. We validate our method with state-of-the-art performance on challenging benchmark datasets: Street View Text, IIIT5k, ICDAR and Synth90k.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.245