西安交通大学电子与信息工程学院,西安,710049
网络首发:2017-01-10,
纸质出版:2017
移动端阅览
张国和, 黄凯, 张斌, 等. 最大稳定极值区域与笔画宽度变换的自然场景文本提取方法[J]. 西安交通大学学报, 2017,51(1):135-140.
A Natural Scene Text Extraction Method Based on the Maximum Stable Extremal Region and Stroke Width Transform[J]. 2017, 51(1): 135-140.
张国和, 黄凯, 张斌, 等. 最大稳定极值区域与笔画宽度变换的自然场景文本提取方法[J]. 西安交通大学学报, 2017,51(1):135-140. DOI: 10.7652/xjtuxb201701021.
A Natural Scene Text Extraction Method Based on the Maximum Stable Extremal Region and Stroke Width Transform[J]. 2017, 51(1): 135-140. DOI: 10.7652/xjtuxb201701021.
针对从背景复杂、视角多变、语言形式多样的场景图像中难以准确提取文本信息的问题
提出了一种基于最大稳定极值区域(MSER)和笔画宽度变换(SWT)场景文本提取方法。该方法结合MSER、SWT算法的优点
采用MSER算法的准确检测文字区域
建立文本候选区域
利用SWT算法计算文本候选区域笔画宽度得到候选文本区域的笔画宽度; 根据笔画宽度图
利用连通域标记建立笔画宽度连通图
然后根据笔画宽度连通图
建立笔画连通图的启发性规则
删除非文本候选区域
并根据文本的几何特征分析及局部自适应窗口最大类间方差(Otsu)分割
有效提取出自然场景图像中的文本
文本提取的准确率、召回率及综合性能分别为0.74、0.64及0.68。仿真实验结果表明
在文本视角多变
字符大小、尺寸、字体各异的复杂条件下
所提方法具有较好的鲁棒性
适用于多语言和多字体混合的场景文本提取。
To extract text information effectively from natural scene image with complex background
multi-orientation perspective and multilingual languages
a scenario text extraction method based on maximum stable extremal region(MSER)and stroke width transform(SWT)is presented. The method combines the merits of MSER and SWT algorithms. It establishes text candidate regions by utilizing MSER algorithm to detect text regions
and SWT algorithm is used to calculate the text stroke width of candidate region to get its stroke width. According to the stroke width graph
the stroke-connected graph is established by using connected component labeling. Then the heuristic rules of stroke-connected graph are established to remove non-text candidate regions according to the stroke-connected graph. By using the geometrical feature analysis and the local adaptive window Otsu segmentation
the text in natural scene images can be extracted effectively. The text extraction accuracy
recall rate and comprehensive performance of this method are 0.74
0.64 and 0.68
respectively. Simulation experiment shows that the method can achieve good robustness for complex background with multi-orientation perspective
various characters and font sizes
and it is suitable for variety of languages and fonts.
ZHANG T Z, ZHAO Y M. Scene text extraction method based on clustering and MRF model [J]. Computer Engineering, 2011, 37(21): 176-181.
MENG Q, SONG Y, ZHANG Y, et al. Text detection in natural scene with edge analysis [C]∥ IEEE International Conference on Image Processing. Piscataway, NJ, USA: IEEE, 2013: 4151-4155.
YI C, TIAN Y. Assistive text reading from natural scene for blind persons [M]. Berlin, Germany: Springer, 2015: 219-241.
NEUMANN L, MATAS J. Real-time scene text localization and recognition [C]∥IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2012: 3538-3545.
QU Y, LIN L, LIAO W, et al. Text localization with hierarchical multiple feature learning [M]. Berlin, Germany: Springer, 2015: 634-643.
MATAS J, CHUM O, URBAN M, et al. Robust wide-baseline stereo from maximally stable extremal regions [J]. Image Vision Computing, 2004, 22(10): 761-767.
EPSHTEIN B, OFEK E, WEXLER Y. Detecting text in natural scenes with stroke width transform [J]. IEEE Conference on Computer Vision and Pattern Recognition, 2010, 119(5): 2963-2970.
OTSU N. A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
CANNY J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698
KITTLER J. On the accuracy of the Sobel edge detector [J]. Image and Vision Computing, 1983, 1(1): 37-42.
WU K, OTOO E, SUZUKI K. Optimizing two-pass connected-component labeling algorithms [J]. Formal Pattern Analysis Applications, 2009, 12(2): 117-135.
LUCAS S M, PANARETOS A, SOSA L, et al. ICDAR 2003 robust reading competitions [C]∥International Conference on Document Analysis and Recognition. Piscataway, NJ, USA: IEEE, 2003: 682-687.
PAN Y F, HOU X, LIU C L. A hybrid approach to detect and localize texts in natural scene images [J]. IEEE Transactions on Image Processing, 2011, 20(3): 800-813.
CHEN H, TSAI S S, SCHROTH G, et al. Robust text detection in natural images with edge-enhanced maximally stable extremal regions [C]∥ 18th IEEE International Conference on Image Processing. Piscataway, NJ, USA: IEEE, 2011: 2609-2612.
张胜杰,查宇飞,李运强,等.一种利用局部结构信息的加权哈希图像检索算法.2016,50(10):78-85.[doi:10.7652/xjtuxb201610012]
周奇才,吴青龙,熊肖磊,等.桁架结构拓扑及截面尺寸优化设计方法.2016,50(9):1-9.[doi:10.7652/xjtuxb201609001]
黄晓冬,孙亮,刘胜蓝.一种判别极端学习的相关反馈图像检索方法.2016,50(8):96-102.[doi:10.7652/xjtuxb201608 016]
张凤娜,张天奎,王东明,等.复杂快中子源编码成像高效模拟方法研究.2016,50(7):118-124.[doi:10.7652/xjtuxb2016 07018]
张泰,张为,刘艳艳.周界视频监控中人员翻越行为检测算法.2016,50(6):47-53.[doi:10.7652/xjtuxb201606008]
郝维娜,令锋超,刘志刚,等.轴承滚珠面型误差激光干涉测量系统的研究.2016,50(6):83-89.[doi:10.7652/xjtuxb 201606013]
瞿磊,王忠,李瑞娜,等.甲醇/生物柴油燃烧颗粒的结构特征研究.2016,50(5):81-86.[doi:10.7652/xjtuxb201605012]
王富平,水鹏朗.采用多尺度方向微分比率的角点检测算法.2016,50(4):68-75.[doi:10.7652/xjtuxb201604011]
姚翠萍,周湘连,王晶,等.纳米金标记细胞的荧光寿命成像及其三维重建.2016,50(4):153-158.[doi:10.7652/xjtuxb 201604023]
朱爱斌,何大勇,邹超,等.刀具磨损图像视差图的非标定方法.2016,50(3):8-15.[doi:10.7652/xjtuxb201603002]
张鹏,陈湘军,阮雅端,等.采用稀疏SIFT特征的车型识别方法.2015,49(12):137-143.[doi:10.7652/xjtuxb201512 022]
崔汪莉,卫军胡,纪鹏,等.基于加权局部梯度直方图的头部三维姿态估计.2015,49(11):71-76.[doi:10.7652/xjtuxb 201511012]
周远,周玉生,刘权,等.一种适用于图像拼接的DSIFT算法研究.2015,49(9):84-90.[doi:10.7652/xjtuxb201509015]
毛彦斌,张选平,杨晓刚.伪DNA密码图像加密算法研究.2015,49(9):91-98.[doi:10.7652/xjtuxb201509016]
刘凯,张立民,孙永威,等.利用深度玻尔兹曼机与典型相关分析的自动图像标注算法.2015,49(6):33-38.[doi:10.7652/xjtuxb201506006]
吴一全,孟天亮,吴诗婳.人工蜂群优化的非下采样Shearlet域引导滤波图像增强.2015,49(6):39-45.[doi:10.7652/xjtuxb201506007]
朱爱斌,胡浩强,何大勇,等.采用频域融合方法的砂轮刀具磨损三维重构技术.2015,49(5):82-86.[doi:10.7652/xjtuxb201505013]
0
浏览量
5
下载量
6
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621