[1]张开玉,邵康一,卢迪. MSER快速自然场景倾斜文本定位算法[J].哈尔滨理工大学学报,2019,(02):81-88.[doi:10.15938/j.jhust.2019.02.012]
 ZHANG Kai yu,SHAO Kang yi,LU Di. MSER Fast Skewed Scenetext Location Algorithm[J].哈尔滨理工大学学报,2019,(02):81-88.[doi:10.15938/j.jhust.2019.02.012]
点击复制

 MSER快速自然场景倾斜文本定位算法()
分享到:

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

卷:
期数:
2019年02期
页码:
81-88
栏目:
电气与电子工程
出版日期:
2019-04-25

文章信息/Info

Title:
 MSER Fast Skewed Scenetext Location Algorithm
文章编号:
1007-2683(2019)02-0081-08
作者:
 张开玉邵康一卢迪
 (哈尔滨理工大学 电气与电子工程学院,黑龙江 哈尔滨 150080)
Author(s):
 ZHANG KaiyuSHAO KangyiLU Di
 (School of Electrical and Electronic Engineering,Harbin University of Science and Technology, Harbin 150080, China)
关键词:
 场景文本最大稳定极值区域层次聚类椭圆拟合
Keywords:
 scene text maximally stable extremal regions hierarchical clustering ellipse fitting
分类号:
TP391.41
DOI:
10.15938/j.jhust.2019.02.012
文献标志码:
A
摘要:
 针对在自然场景中文本定位需要大量样本训练导致算法运行速度较慢且倾斜文本难以定位的问题,提出了一种基于最大稳定极值区域(maximally stable extremal regions,MSER)结合层次聚类的快速自然场景倾斜文本定位算法。利用MSER椭圆拟合的方法对图片进行最大极值稳定区域的选取,并根据拟合椭圆的自身特征和在图像上的位置特征,过滤掉大部分的非文本区域,筛选出文本候选区域。运用层次聚类的思想,快速对文本区域逐层聚类融合,最终将单个的文本区域合并成单词区域,实现高效的倾斜场景文本定位。实验结果表明,与传统的定位算法相比,该算法在没有损失定位精度的情况下运算速度有明显的提升。
Abstract:
 Aiming at the problem that text localization requires a large number of training samples in natural scenes, which leads to low speed of algorithm running and it is difficult to locate skewed text, a fast natural scene skewed text localization algorithm based on maximally stable extremal regions (MSER) with hierarchical clustering is proposed  The method of MSER ellipse fitting is used to select the maximally stable extremal regions of the images, and according to the characteristics of the fitting ellipse and its position on the images, the majority of nontext regions are filtered out and the text candidate regions are selected By using the idea of hierarchical clustering, the text regions can be clustered gradually and merged into text regions rapidly. Finally the individual text regions are merged into word regions, which can achieve efficient localization of skewed scenes Experimental results show that the speed of this algorithm has improved significantly without loss of locating accuracy compared with traditional positioning algorithms.

参考文献/References:

[1]YE Q,DOERMANN D. Text Detection and Recognition in Imagery: A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(7): 1480.
[2]CHEN XR, YUILLE A. Detering and Reading Text in Natural Scenes[C]// IEEE Computer Vision and Pattern Recognition,Washington,D.C.,USA,2004:366.
[3]尹芳,郑亮,陈田田.基于Adaboost的视频文本定位[J]. 哈尔滨理工大学学报, 2017, 22(1):103.
[4]KOO H, KIM D.Scene Text Detection Via Connected Component Clustering and Nontext Filtering[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2013,22(6): 2296.
[5]YIN X C,YIN X W,HUANGK Z,et al.Robust Text Detection in Natural Scene Images[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 36(5): 970.
[6]SHAHAB A, SHAFAIT F, DENGEL A.ICDAR 2011 Robust Reading Competition Challenge 2:reading Text in Scene Image[C]// Proceeding of International Conference on Document Analysis and Recognition, IEEE, Beijing, China, 2011(1):1491.
[7]KARATZAS D, SHAFAIT F, UCHIDA S, et al.ICDAR 2013 Robust Reading Competiton[C]// Proceeding of International Conference on Document Analysis and Recognition, IEEE ,Washington, USA, 2013(1):1484.
[8]KARATZAS D, LU S, SHAFAIT F, et al. ICDAR 2015 Competition on Robust Reading[C]// International Conference on Document Analysis and Recognition, IEEE Computer Society, Tunis, Tunisia, 2015(1):1156.
[9]朱安娜.基于卷积神经网络的场景文本定位及多方向字符识别研究[D].武汉:华中科技大学,2016:26.
[10]FISCHLER M A, BOLLES R C. Random Sample Consensus:A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography[J]. Communications of the acm, 1981, 24(6): 381.
[11]高士林,吉力新,李绍梅,等.基于MSER拟合椭圆的快速场景文本定位算法[J].计算机工程与设计,2015(3):693.
[12]MATAS J, CHUM O, URBAN M, et al. Robust Widebaseline Stereo from Maximally Stable Extremal Regions[J]. Image & Vision Computing, 2004, 22(10): 761.
[13]NEUMANN L, MATAS J. Realtime Scene Text Localization and Recognition[C]// IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Providence, RI, USA, 2012(1):3538.
[14]姚聪. 自然图像中文字检测与识别研究[D]. 武汉:华中科技大学, 2014: 24.
[15]ASIBA T, SHWETA A D. Text Detection Using MSER and Stroke Width Transform[C]// Communication Systems and Network Technologies, 2015 Fifth International Conference on, Gwalior, India, 2015(1): 568.
[16]LUCAS S M, PANARETOS A, SOSA L, et al. ICDAR 2003 Robust Reading Competitions[C]// International Conference on Document Analysis and Recognition, IEEE, Edinburgh, UK, 2003(1):682.
[17]HU H, ZHANG C, LUO Y,et al. WordSup: Exploiting Word Annotations for Character Based Text Detection[C]// International Conference on Computer Vision, IEEE, Venice, Italy, 2017(1): 4950.
[18]TIAN Z, HUANG W, HE T, et al. Detecting Text in Natural Image with Connectionist Text Proposal Network[C]// European Conference on Computer Vision. Springer, Cham, 2016(1): 56.
[19]ZHONG Z, JIN L, ZHANG S, et al. DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images[J]. Architecture Science, 2016(12): 1.
[20]ZHANG C, YAO C, SHI B, et al. Automatic Discrimination Oftext and Nontext Natural Images[C]// International Conference on Document Analysis and Recognition, IEEE, Tunis, Tunisia, 2015(1): 886.

相似文献/References:

[1]孙永全,郭建英,陈洪科,等.AMSAA模型可靠性增长预测方法的改进[J].哈尔滨理工大学学报,2010,(05):49.
 SUN Yong-quan,GUO Jian-ying,CHEN Hong-ke,et al.An Improved Reliability Growth Prediction Algorithm Based on AMSAA Model[J].哈尔滨理工大学学报,2010,(02):49.
[2]滕志军,李晓霞,郑权龙,等.矿井巷道的MIMO信道几何模型及其信道容量分析[J].哈尔滨理工大学学报,2012,(02):14.
 TENG Zhi-jun,LI Xiao-xia,ZHENG Quan-long.Geometric Model for Mine MIMO Channels and Its Capacity Analysis[J].哈尔滨理工大学学报,2012,(02):14.
[3]李艳苹,张礼勇.新训练序列下的改进OFDM符号定时算法[J].哈尔滨理工大学学报,2012,(02):19.
 LI Yan-ping,ZHANG Li-yong.An Improved Algorithm of OFDM Symbol Timing Based on A New Training Sequence[J].哈尔滨理工大学学报,2012,(02):19.
[4]赵彦玲,车春雨,铉佳平,等.钢球全表面螺旋线展开机构运动特性分析[J].哈尔滨理工大学学报,2013,(01):37.
 ZHAO Yan-ling,CHE Chun-yu,XUAN Jia-ping,et al.[J].哈尔滨理工大学学报,2013,(02):37.
[5]李冬梅,卢旸,刘伟华,等.一类具有连续接种的自治SEIR传染病模型[J].哈尔滨理工大学学报,2013,(01):73.
 LI Dong-mei,LU Yang,LIU Wei-hua.[J].哈尔滨理工大学学报,2013,(02):73.
[6]华秀英,刘文德.奇Hamiltonian李超代数偶部的非负Z-齐次导子空间[J].哈尔滨理工大学学报,2013,(01):76.
 HUA Xiu-ying,LIU Wen-de.[J].哈尔滨理工大学学报,2013,(02):76.
[7]桂存兵,刘洋,何业军,等.基于LCC谐振电路阻抗匹配的光伏发电最大功率点跟踪[J].哈尔滨理工大学学报,2013,(01):90.
 GUI Cun-bing,LIU Yong,HE Ye-jun.[J].哈尔滨理工大学学报,2013,(02):90.
[8]翁凌,闫利文,夏乾善,等.PI/TiC@Al2O3复合薄膜的制备及其电性能研究[J].哈尔滨理工大学学报,2013,(02):25.
 WENG Ling,YAN Li-wen,XIA Qian-shan.[J].哈尔滨理工大学学报,2013,(02):25.
[9]姜彬,林爱琴,王松涛,等.高速铣刀安全性设计理论与方法[J].哈尔滨理工大学学报,2013,(02):63.
 JIANG Bin,LIN Ai-qin,WANG Song-tao,et al.[J].哈尔滨理工大学学报,2013,(02):63.
[10]李星纬,李晓东,张颖彧,等.EVOH 磺酸锂电池隔膜的制备及微观形貌[J].哈尔滨理工大学学报,2013,(05):18.
 LI Xing- wei,LI Xiao- dong,ZHANG Ying- yu,et al.The Preparation and Microcosmic Morphology oEVOH- SO Li Lithium Ion Battery Septum[J].哈尔滨理工大学学报,2013,(02):18.

备注/Memo

备注/Memo:
 收稿日期:2017-04-20
基金项目:黑龙江省自然科学基金(面上项目)(F2016022)
作者简介:
邵康一(1992—),男,硕士研究生;
卢迪(1971—),女,博士后,教授
通信作者:
张开玉(1978—),男,博士研究生,副教授,E-mail:gotoayun@126.com
更新日期/Last Update: 2019-05-17