Scene Text Script Identification with Convolutional Recurrent Neural Networks

被引：0

作者：

Mei, Jieru ^{[1
]}

Dai, Luo ^{[2
]}

Shi, Baoguang ^{[2
]}

Bai, Xiang ^{[2
]}

机构：

[1] Huazhong Univ Sci & Technol, Sch Automat, Wuhan 430074, Hubei, Peoples R China

[2] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Hubei, Peoples R China

来源：

2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) | 2016年

基金：

中国国家自然科学基金;

关键词：

FEATURES;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：4053 / 4058

页数：6