An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
Top Cited Papers
- 29 December 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 39 (11), 2298-2304
- https://doi.org/10.1109/tpami.2016.2646371
Abstract
Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed. Compared with previous systems for scene text recognition, the proposed architecture possesses four distinctive properties: (1) It is end-to-end trainable, in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It is not confined to any predefined lexicon and achieves remarkable performances in both lexicon-free and lexicon-based scene text recognition tasks. (4) It generates an effective yet much smaller model, which is more practical for realworld application scenarios. The experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets, demonstrate the superiority of the proposed algorithm over the prior arts. Moreover, the proposed algorithm performs well in the task of image-based music score recognition, which evidently verifies the generality of it.Keywords
Funding Information
- National Natural Science Foundation of China (NSFC) (61573160, 61222308)
This publication has 26 references indexed in Scilit:
- Accurate Scene Text Recognition Based on Recurrent Neural NetworkPublished by Springer Science and Business Media LLC ,2015
- Label Embedding: A Frugal Baseline for Text RecognitionInternational Journal of Computer Vision, 2014
- Text Detection and Recognition in Imagery: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- A Unified Framework for Multioriented Text Detection and RecognitionIEEE Transactions on Image Processing, 2014
- Word Spotting and Recognition with Embedded AttributesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Optical music recognition: state-of-the-art and open issuesInternational Journal of Multimedia Information Retrieval, 2012
- ICDAR 2003 robust reading competitions: entries, results, and future directionsInternational Journal on Document Analysis and Recognition (IJDAR), 2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Some approaches to best-match file searchingCommunications of the ACM, 1973