An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

07/21/2015
by   Baoguang Shi, et al.
0

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 real-world 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2018

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes

Recently, models based on deep neural networks have dominated the fields...
research
12/31/2018

Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks

Unconstrained text recognition is an important computer vision task, fea...
research
11/21/2016

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

This paper presents an end-to-end trainable fast scene text detector, na...
research
06/04/2018

NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition

Scene text recognition has attracted a great many researches for decades...
research
06/06/2023

Looking and Listening: Audio Guided Text Recognition

Text recognition in the wild is a long-standing problem in computer visi...
research
06/02/2018

SCAN: Sliding Convolutional Attention Network for Scene Text Recognition

Scene text recognition has drawn great attentions in the community of co...
research
01/13/2016

Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues

Recognizing scene text is a challenging problem, even more so than the r...

Please sign up or login with your details

Forgot password? Click here to reset