Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
Preprint
Abstract
We present recursive recurrent neural networks with attention modeling (R$^2$AM) 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.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Reading Text in the Wild with Convolutional Neural NetworksInternational Journal of Computer Vision, 2015
- Accurate Scene Text Recognition Based on Recurrent Neural Network2015
- Label Embedding: A Frugal Baseline for Text RecognitionInternational Journal of Computer Vision, 2014
- Deep Features for Text Spotting2014
- Detecting texts of arbitrary orientations in natural images2012
- Large-Lexicon Attribute-Consistent Text Recognition in Natural Images2012
- Enforcing similarity constraints with integer programming for better scene text recognition2011
- Word Spotting in the Wild2010
- Detecting and reading text in natural scenes2004
- Generalization of backpropagation with application to a recurrent gas market modelNeural Networks, 1988