The Community for Technology Leaders
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Las Vegas, NV, United States
June 27, 2016 to June 30, 2016
ISSN: 1063-6919
ISBN: 978-1-4673-8851-1
pp: 2231-2239
ABSTRACT
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.
INDEX TERMS
Feature extraction, Optical character recognition software, Predictive models, Recurrent neural networks, Character recognition, Text recognition, Computational modeling
CITATION

C. Lee and S. Osindero, "Recursive Recurrent Nets with Attention Modeling for OCR in the Wild," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, United States, 2016, pp. 2231-2239.
doi:10.1109/CVPR.2016.245
182 ms
(Ver 3.3 (11022016))