A novel text structure feature extractor for Chinese scene text detection and recognition

Xiaohang Ren, Kai Chen, Xiaokang Yang, Yi Zhou, Jianhua He, Jun Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Scene text information extraction plays an important role in many computer vision applications. Unlike most existing text extraction algorithms for English texts, in this paper, we focus on Chinese texts, which are more complex in stroke and structure. To tackle this challenging problem, we propose a novel convolutional neural network (CNN) based text structure feature extractor for Chinese texts. Each Chinese character contains its specific types and combination of text structure components, which is rarely seen in backgrounds. Thus, different from the features only applicable to one text extraction stage (text detection or text recognition), the text structure component feature is suitable for both Chinese text detection and recognition. A text structure component detector (TSCD) layer is designed to detect the large amount of component types, which is the most challenging part of extracting text structure component features. Through statistical classification various types of text structure component are detected by their specially designed convolutional units in the TSCD layer. With the TSCD layer, the CNN has improvements in the accuracy and uniqueness of text feature description. In the evaluation, both text detection and recognition algorithms based on the proposed text structure feature extractor achieve state-of-the-art results in two datasets.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR
PublisherIEEE
Pages3380-3385
Number of pages6
ISBN (Electronic)978-1-5090-4847-2
DOIs
Publication statusPublished - 13 Apr 2017
Event23rd International Conference on Pattern Recognition: ICPR 2016 - Cancun, Mexico
Duration: 4 Dec 20168 Dec 2016

Conference

Conference23rd International Conference on Pattern Recognition
CountryMexico
CityCancun
Period4/12/168/12/16

Fingerprint

Detectors
Neural networks
Computer vision

Bibliographical note

-

Cite this

Ren, X., Chen, K., Yang, X., Zhou, Y., He, J., & Sun, J. (2017). A novel text structure feature extractor for Chinese scene text detection and recognition. In 2016 23rd International Conference on Pattern Recognition, ICPR (pp. 3380-3385). IEEE. https://doi.org/10.1109/ICPR.2016.7900156
Ren, Xiaohang ; Chen, Kai ; Yang, Xiaokang ; Zhou, Yi ; He, Jianhua ; Sun, Jun. / A novel text structure feature extractor for Chinese scene text detection and recognition. 2016 23rd International Conference on Pattern Recognition, ICPR. IEEE, 2017. pp. 3380-3385
@inproceedings{b179e250a2e8447f932682d15d87be1a,
title = "A novel text structure feature extractor for Chinese scene text detection and recognition",
abstract = "Scene text information extraction plays an important role in many computer vision applications. Unlike most existing text extraction algorithms for English texts, in this paper, we focus on Chinese texts, which are more complex in stroke and structure. To tackle this challenging problem, we propose a novel convolutional neural network (CNN) based text structure feature extractor for Chinese texts. Each Chinese character contains its specific types and combination of text structure components, which is rarely seen in backgrounds. Thus, different from the features only applicable to one text extraction stage (text detection or text recognition), the text structure component feature is suitable for both Chinese text detection and recognition. A text structure component detector (TSCD) layer is designed to detect the large amount of component types, which is the most challenging part of extracting text structure component features. Through statistical classification various types of text structure component are detected by their specially designed convolutional units in the TSCD layer. With the TSCD layer, the CNN has improvements in the accuracy and uniqueness of text feature description. In the evaluation, both text detection and recognition algorithms based on the proposed text structure feature extractor achieve state-of-the-art results in two datasets.",
author = "Xiaohang Ren and Kai Chen and Xiaokang Yang and Yi Zhou and Jianhua He and Jun Sun",
note = "-",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICPR.2016.7900156",
language = "English",
pages = "3380--3385",
booktitle = "2016 23rd International Conference on Pattern Recognition, ICPR",
publisher = "IEEE",
address = "United States",

}

Ren, X, Chen, K, Yang, X, Zhou, Y, He, J & Sun, J 2017, A novel text structure feature extractor for Chinese scene text detection and recognition. in 2016 23rd International Conference on Pattern Recognition, ICPR. IEEE, pp. 3380-3385, 23rd International Conference on Pattern Recognition, Cancun, Mexico, 4/12/16. https://doi.org/10.1109/ICPR.2016.7900156

A novel text structure feature extractor for Chinese scene text detection and recognition. / Ren, Xiaohang; Chen, Kai; Yang, Xiaokang; Zhou, Yi; He, Jianhua; Sun, Jun.

2016 23rd International Conference on Pattern Recognition, ICPR. IEEE, 2017. p. 3380-3385.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A novel text structure feature extractor for Chinese scene text detection and recognition

AU - Ren, Xiaohang

AU - Chen, Kai

AU - Yang, Xiaokang

AU - Zhou, Yi

AU - He, Jianhua

AU - Sun, Jun

N1 - -

PY - 2017/4/13

Y1 - 2017/4/13

N2 - Scene text information extraction plays an important role in many computer vision applications. Unlike most existing text extraction algorithms for English texts, in this paper, we focus on Chinese texts, which are more complex in stroke and structure. To tackle this challenging problem, we propose a novel convolutional neural network (CNN) based text structure feature extractor for Chinese texts. Each Chinese character contains its specific types and combination of text structure components, which is rarely seen in backgrounds. Thus, different from the features only applicable to one text extraction stage (text detection or text recognition), the text structure component feature is suitable for both Chinese text detection and recognition. A text structure component detector (TSCD) layer is designed to detect the large amount of component types, which is the most challenging part of extracting text structure component features. Through statistical classification various types of text structure component are detected by their specially designed convolutional units in the TSCD layer. With the TSCD layer, the CNN has improvements in the accuracy and uniqueness of text feature description. In the evaluation, both text detection and recognition algorithms based on the proposed text structure feature extractor achieve state-of-the-art results in two datasets.

AB - Scene text information extraction plays an important role in many computer vision applications. Unlike most existing text extraction algorithms for English texts, in this paper, we focus on Chinese texts, which are more complex in stroke and structure. To tackle this challenging problem, we propose a novel convolutional neural network (CNN) based text structure feature extractor for Chinese texts. Each Chinese character contains its specific types and combination of text structure components, which is rarely seen in backgrounds. Thus, different from the features only applicable to one text extraction stage (text detection or text recognition), the text structure component feature is suitable for both Chinese text detection and recognition. A text structure component detector (TSCD) layer is designed to detect the large amount of component types, which is the most challenging part of extracting text structure component features. Through statistical classification various types of text structure component are detected by their specially designed convolutional units in the TSCD layer. With the TSCD layer, the CNN has improvements in the accuracy and uniqueness of text feature description. In the evaluation, both text detection and recognition algorithms based on the proposed text structure feature extractor achieve state-of-the-art results in two datasets.

UR - http://ieeexplore.ieee.org/document/7900156/

UR - http://www.scopus.com/inward/record.url?scp=85018498337&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2016.7900156

DO - 10.1109/ICPR.2016.7900156

M3 - Conference contribution

AN - SCOPUS:85018498337

SP - 3380

EP - 3385

BT - 2016 23rd International Conference on Pattern Recognition, ICPR

PB - IEEE

ER -

Ren X, Chen K, Yang X, Zhou Y, He J, Sun J. A novel text structure feature extractor for Chinese scene text detection and recognition. In 2016 23rd International Conference on Pattern Recognition, ICPR. IEEE. 2017. p. 3380-3385 https://doi.org/10.1109/ICPR.2016.7900156