|   | 
Author Suman Ghosh; Ernest Valveny
Title Visual attention models for scene text recognition Type Conference Article
Year 2017 Publication 14th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages
Abstract arXiv:1706.01487
In this paper we propose an approach to lexicon-free recognition of text in scene images. Our approach relies on a LSTM-based soft visual attention model learned from convolutional features. A set of feature vectors are derived from an intermediate convolutional layer corresponding to different areas of the image. This permits encoding of spatial information into the image representation. In this way, the framework is able to learn how to selectively focus on different parts of the image. At every time step the recognizer emits one character using a weighted combination of the convolutional feature vectors according to the learned attention model. Training can be done end-to-end using only word level annotations. In addition, we show that modifying the beam search algorithm by integrating an explicit language model leads to significantly better recognition results. We validate the performance of our approach on standard SVT and ICDAR'03 scene text datasets, showing state-of-the-art performance in unconstrained text recognition.
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume (down) Series Issue Edition
Area Expedition Conference ICDAR
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ GhV2017b Serial 3080
Permanent link to this record