Chinese text localization based on Adaboost algorithm in natural images

doi:10.3778/j.issn.1002-8331.1506-0160

Computer Engineering and Applications ›› 2017, Vol. 53 ›› Issue (4): 200-204.DOI: 10.3778/j.issn.1002-8331.1506-0160

Previous Articles Next Articles

Chinese text localization based on Adaboost algorithm in natural images

YIN Fang1，2, ZHENG Liang1, CHEN Tiantian1

1.School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
2.Instrument Science and Technology Postdoctoral Research Station, Harbin University of Science and Technology, Harbin 150080, China

Online:2017-02-15 Published:2017-05-11

基于Adaboost算法的场景中文文本定位

尹芳1，2，郑亮1，陈田田1

1.哈尔滨理工大学计算机科学与技术学院，哈尔滨 150080
2.哈尔滨理工大学仪器科学与技术博士后科研流动站，哈尔滨 150080

Abstract

Abstract: A novel Chinese text localization method based on Adaboost in natural images is proposed in this paper. Firstly, the text regions are detected using the edge feature, where digital image is processed by edge extraction and binarization, then connected domain analysis is used to remove non-text regions and get candidate text regions. Secondly, a strong classifier of Adaboost with CART（Classification And Regression Tree） is constructed by using the four classes Chinese text features that are extracted by analyzing the text areas. Finally, the correct text areas are got after the candidate regions are send into the strong classifier. The experimental results show that not only can this method achieve a good effect on the text location in the natural images including the images with text of various fonts, sizes and colors but also realize high recall rate and precision rate.

Key words: text location, text recognition, connected domain, classification and regression tree

摘要： 提出了一种基于Adaboost算法的场景中文文本定位的新方法。首先利用边缘特征进行文本区域的检测，即对数字图像进行边缘提取、二值化处理，然后通过连通域分析去除明显的非字符连通域，并获得候选的文本区域。对场景中文文本区域进行分析，提取了场景中文文本的4类特征，并利用这4类特征经过分类与回归决策树构造了Adaboost强分类器。将候选文本区域送入强分类器，得到正确的文本区域。实验结果表明方法不仅对场景文本图像中字体、大小和颜色多变的文本具有很好的定位效果，而且具有很高的召回率和准确率。

关键词: 文本定位, 文本识别, 连通域, 分类与回归决策树

YIN Fang1，2, ZHENG Liang1, CHEN Tiantian1. Chinese text localization based on Adaboost algorithm in natural images[J]. Computer Engineering and Applications, 2017, 53(4): 200-204.

尹芳1，2，郑亮1，陈田田1. 基于Adaboost算法的场景中文文本定位[J]. 计算机工程与应用, 2017, 53(4): 200-204.

[1]	ZHAO Fan, ZHANG Lin, WEN Zhiquan, YANG Linlin, LIN Guangfeng. Direct and Efficient Natural Scene Chinese Character Approaching Spotting Method [J]. Computer Engineering and Applications, 2021, 57(6): 159-167.
[2]	WANG Deqing, Wushouer·Silamu, XU Miaomiao. Review of Research on Scene Text Recognition Technology [J]. Computer Engineering and Applications, 2020, 56(18): 1-15.
[3]	QIU Ningjia, SHEN Zhuorui, WANG Hui, WANG Peng. Semi-supervised Learning Optimization Algorithm for Communication Spam Text Recognition [J]. Computer Engineering and Applications, 2020, 56(17): 121-128.
[4]	ZHENG Zubing, SHENG Guanqun, XIE Kai, TANG Xingong, WEN Chang, LI Changsheng. Intelligent Medical Bills Recognition Method Based on Combined Network Model [J]. Computer Engineering and Applications, 2020, 56(12): 141-148.
[5]	YANG Biao, DU Xiaoyu. Natural Scene Text Detection Algorithm Based on Improved EAST [J]. Computer Engineering and Applications, 2019, 55(18): 161-165.
[6]	WU Xueyan, WANG Shuihua, ZHANG Yudong. Survey on theory and application of k-Nearest-Neighbors algorithm [J]. Computer Engineering and Applications, 2017, 53(21): 1-7.
[7]	LIU Yaya, YU Fengqin, CHEN Ying. Text location in image based on connected-component and statistical features [J]. Computer Engineering and Applications, 2016, 52(5): 165-168.
[8]	PENG Lirong1, ZHOU Lei2. Fusion of DM with cognitive and behavior calculating models for improving teaching quality [J]. Computer Engineering and Applications, 2014, 50(9): 237-241.
[9]	WANG Lei1，2, WANG Hanli1，2, HE Lianghua1，2. License plate recognition based on double-edge detection [J]. Computer Engineering and Applications, 2013, 49(8): 169-173.
[10]	YU Ming, GUO Qian, WANG Dongzhuang, YU Yang. Improved connectivity-based layout segmentation method [J]. Computer Engineering and Applications, 2013, 49(17): 195-198.
[11]	HUANG Siwei1, TIAN Xiaolin1, SUN Yankui2. Anterior chamber OCT images edge detection and extraction of feature corner points [J]. Computer Engineering and Applications, 2012, 48(25): 159-162.
[12]	ZHAO Hui1，2, WANG Yunjia1，2. Fusing muti-scale segmentation into CART algorithm on coal gangue extraction [J]. Computer Engineering and Applications, 2012, 48(22): 222-225.
[13]	LIU Fangzhou1，TAO Jianhua2. Automatic feature template generation for intonational phrase prediction [J]. Computer Engineering and Applications, 2011, 47(16): 19-21.
[14]	ZHOU Huican1，LIU Qiong1，WANG Yaonan2. Precise text location based on region search and invariable moment classification [J]. Computer Engineering and Applications, 2011, 47(10): 164-168.
[15]	ZHANG Jian-fei ^1，2，MA Yan¹，JI Wei-dong ^1，3. Area statistical method of void contents for wood-based panel based on image processing technique [J]. Computer Engineering and Applications, 2009, 45(21): 183-184.

Chinese text localization based on Adaboost algorithm in natural images

基于Adaboost算法的场景中文文本定位

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics