Printed mathematical expressions extraction method based on ICSA-SVM and K-L transform

doi:10.3778/j.issn.1002-8331.2010.15.043

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (15): 146-149.DOI: 10.3778/j.issn.1002-8331.2010.15.043

• 图形、图像、模式识别 • Previous Articles Next Articles

Printed mathematical expressions extraction method based on ICSA-SVM and K-L transform

ZHANG Can-long^1，3，TANG Yan-ping²，WANG Qiang¹，WEI Chun-rong¹

1.College of Computer Science and Information Engineering，Guangxi Normal University，Guilin，Guangxi 541004，China
2.School of Material Science and Engineering，Guilin University of Electronic Technology，Guilin，Guangxi 541004，China
3.School of Aeronautics & Astronautics，Shanghai Jiaotong University，Shanghai 200240，China

Received:2009-12-08 Revised:2010-03-17 Online:2010-05-21 Published:2010-05-21
Contact: ZHANG Can-long

一种印刷体数学公式优化提取策略

张灿龙^1，3，唐艳平²，王强¹，韦春荣¹

1.广西师范大学计算机科学与信息工程学院，广西桂林 541004
2.桂林电子科技大学材料科学与工程学院，广西桂林 541004
3.上海交通大学航空航天学院，上海 200240

通讯作者: 张灿龙

Abstract

Abstract: A new approach for separating both isolated and embedded expressions in printed Chinese technical documents is presented，which includes two steps：line classification and symbol recognition.In the approach，K-L transform is applied to eliminate interrelation among line features and extract symbol features，and immune clone selection algorithm is used to optimize parameters of line classifier and symbol classifier based on support vector machine.The testing result to about 300 printed Chinese technical documents indicates that the expressions extraction accuracy is 94% above.

Key words: printed mathematical expression, support vector machine, K-L transform, Immune Clone Selection

摘要： 提出了一种先版面行分类后符号识别的印刷体数学公式提取策略。策略中两次应用K-L变换，分别完成版面行特征的降维和公式符号特征的提取，并采用免疫克隆选择算法优化支持向量机的训练参数，以构建出最优的版面行分类器和公式符号识别器。通过对300多份印刷体中文科技文档进行扫描识别测试，所得结果的公式提取率可达94%以上。

关键词: 印刷体数学公式, 支持向量机, K-L变换, 免疫克隆选择

CLC Number:

TP391.41

ZHANG Can-long^1，3，TANG Yan-ping²，WANG Qiang¹，WEI Chun-rong¹. Printed mathematical expressions extraction method based on ICSA-SVM and K-L transform[J]. Computer Engineering and Applications, 2010, 46(15): 146-149.

张灿龙^1，3，唐艳平²，王强¹，韦春荣¹. 一种印刷体数学公式优化提取策略 [J]. 计算机工程与应用, 2010, 46(15): 146-149.

[1]	GAO Yikai, PENG Li, XU Longzhuang. Flame Recognition Method Using TWSVM with Improved Artificial Fish Swarm Algorithm [J]. Computer Engineering and Applications, 2021, 57(8): 204-213.
[2]	HAN Weiyu, CHENG Longsheng. Research on Roling Bearing Failure Mode Classification Based on MTS and SVM [J]. Computer Engineering and Applications, 2021, 57(6): 239-246.
[3]	LEI Henglin, Gulanbaier Tuerhong, Mairidan Wushouer, ZHANG Dongmei. Review of Novelty Detection [J]. Computer Engineering and Applications, 2021, 57(5): 47-55.
[4]	WEN Jiebin, YANG Wenzhong, MA Guoxiang, ZHANG Zhihao, LI Hailei. Micro-expression Recognition Based on Apex Frame Optical Flow and Convolutional Autoencoder [J]. Computer Engineering and Applications, 2021, 57(4): 127-133.
[5]	XU Xianfeng, CAI Lulu, ZHANG Li. Photovoltaic Power Generation Prediction Algorithm Based on MLP and DBN [J]. Computer Engineering and Applications, 2021, 57(3): 266-272.
[6]	LI Junxia, ZHANG Qin, ZHENG Guimei. Overview of Human Posture Recognition by Ultra-wideband Radar [J]. Computer Engineering and Applications, 2021, 57(3): 14-23.
[7]	CHEN Fujian, XIE Weixin, XIA Ting. Adaptive Anti-occlusion Target Tracking Algorithm Based on LCT+ [J]. Computer Engineering and Applications, 2021, 57(22): 190-198.
[8]	YANG Quan. SVM Algorithm for N1+N2 Structure Syntax Relation Determination [J]. Computer Engineering and Applications, 2021, 57(20): 104-108.
[9]	GAO Jin, ZHAO Yunpeng, Godfred Kim Mensah, LI Xinyun, LIU Zhifen, CHEN Junjie, GUO Hao. Research on Spatial Dynamics Analysis and Classification of Resting-State Functional Brain Connections [J]. Computer Engineering and Applications, 2021, 57(2): 150-155.
[10]	QIN Boyu, HAO Xiaoyan, LIU Yongfang. Frame Disambiguation of FrameNet Based on SVM and CRF Two-Stage Model [J]. Computer Engineering and Applications, 2021, 57(18): 255-262.
[11]	ZHENG Linwen, ZHOU Jinzhi, HUANG Jing. Application of Deep Sparse Auto-Encoders in ECG Feature Extraction [J]. Computer Engineering and Applications, 2021, 57(11): 156-161.
[12]	WEN Tingxin, KONG Xiangbo. Research on Extreme Risk Warning in Financial Market from Imbalance Distribution of Samples [J]. Computer Engineering and Applications, 2020, 56(8): 256-260.
[13]	CHEN Feiyu, YUE Wenbin, RAO Yinglu, XING Jinhao, MA Xiaojing. Autonomous Precision Landing of Drone Based on Improved TLD Algorithm [J]. Computer Engineering and Applications, 2020, 56(7): 247-254.
[14]	MA Ling, LUO Xiaoshu, JIANG Pinqun. Research on Dot Matrix Character Recognition Based on Template Matching and Support Vector Machine [J]. Computer Engineering and Applications, 2020, 56(4): 134-139.
[15]	ZHANG Zhonglin, FENG Yibang, ZHAO Zhongkai. Oversampling Method for Unbalanced Data Sets Based on SVM [J]. Computer Engineering and Applications, 2020, 56(23): 220-228.

Printed mathematical expressions extraction method based on ICSA-SVM and K-L transform

一种印刷体数学公式优化提取策略

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics