Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
Authors:
- Chen-Yu LeeCLChen-Yu Lee
- Simon OsinderoSOSimon Osindero
Top Cited Papers
- 1 June 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 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.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Recurrent convolutional neural network for object recognition2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Caffe2014
- Word Spotting and Recognition with Embedded AttributesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Scene Text Recognition Using Part-Based Tree-Structured Character Detection2013
- Top-down and bottom-up cues for scene text recognition2012
- Real-time scene text localization and recognition2012
- Scene Text Recognition using Higher Order Language Priors2012
- ICDAR 2003 robust reading competitions2005
- Learning Internal Representations by Error Propagation1985