Scene text script identification with Convolutional Recurrent Neural Networks

Script identification for scene text images is a challenging task. This paper describes a novel deep neural network structure that efficiently identifies scripts of images. In our design, we exploit two important factors, namely the image representation, and the spatial dependencies within text line...

Full description

Saved in:
Bibliographic Details
Published in2016 23rd International Conference on Pattern Recognition (ICPR) pp. 4053 - 4058
Main Authors Jieru Mei, Luo Dai, Baoguang Shi, Xiang Bai
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2016
Subjects
Convolution
Feature extraction
Hidden Markov models
Image representation
Logic gates
Recurrent neural networks
Online AccessGet full text
DOI10.1109/ICPR.2016.7900268

Cover

More Information
Summary:Script identification for scene text images is a challenging task. This paper describes a novel deep neural network structure that efficiently identifies scripts of images. In our design, we exploit two important factors, namely the image representation, and the spatial dependencies within text lines. To this end, we bring together a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) into one end-to-end trainable network. The former generates rich image representations, while the latter effectively analyzes long-term spatial dependencies. Besides, on top of the structure, we adopt an average pooling structure in order to deal with input images of arbitrary sizes. Experiments on several datasets, including SIW-13 and CVSI2015, demonstrate that our approach achieves superior performance, compared with previous approaches.
DOI:10.1109/ICPR.2016.7900268