期刊文献+

基于Laplace变换的视频文本检测

Video Text Detection Based on Laplace Transform
下载PDF
导出
摘要 本文提出了一种基于Laplace变换的视频图像水平文本检测算法。首先用Laplace变换对图像滤波,并根据梯度信息用K-均值方法对像素点聚类,得到候选文本区;然后用投影算法对候选文本区进行边缘精确,得到候选文本块;最后分析候选文本块的几何特性,进行文本验证。本文算法在公共数据库上的测试结果表明了算法的可行性和有效性。 The paper proposes a horizontal video text detection method based on Laplace transform. Firstly, we use K-means to cluster pixels on the Laplace-i ltered image to obtain candidate text region based on gradient information. Then, projection proi le is applied on candidate text region for boundary rei nement and we obtain candidate text blocks. Finally, text identii cation is performed to remove non-text blocks by analyzing geometrical properties. The experimental results on public dataset show the ef ectiveness and feasibility of the proposed method.
作者 朱志坚
机构地区 湖南电视台
出处 《广播与电视技术》 2015年第5期71-74,共4页 Radio & TV Broadcast Engineering
关键词 视频文本检测 LAPLACE变换 边缘精确 文本验证 Video text detection,Laplace transform,Boundary rei nement,Text identii cation
  • 相关文献

参考文献11

  • 1Yi Cheng Wei,Chang Hong Lin.A robust video text detection approach using SVM[J]. Expert Systems With Applications . 2012 (12)
  • 2Shivakumara, Palaiahnakote,Phan, Trung Quy,Tan, Chew Lim.A Laplacian approach to multi-oriented text detection in video. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2011
  • 3Trung Q P,Palaiahnakote S,Chew L T.A Laplacian method for video text detection. IEEE International Conference on Document Analysis and Recognition . 2009
  • 4Yi, C.,Tian, Y.Localizing Text in Scene Images by Boundary Clustering, Stroke Segmentation, and String Fragment Classification. Image Processing, IEEE Transactions on . 2012
  • 5Zhu C,Ouyang Y,Gao L,et al.An automatic video textdetection,localization and extraction approach. AdvancedI nternet Based Systems and Applications . 2009
  • 6Palaiahnakote Shivakumara,Rushi Padhuman Sreedhar,Trung Quy Ph.Multioriented Video Scene Text Detection Through Bayesian Classification and Boundary Growing. IEEE Transactions on Circuits and Systems for Video Technology . 2012
  • 7Hua, Xian-Sheng,Wenyin, Liu,Zhang, Hong-Jiang.An Automatic Performance Evaluation Protocol for Video Text Detection Algorithms. IEEE Transactions on Circuits and Systems for Video Technology . 2004
  • 8朱宁波,张春凤,郑碧娟.基于自适应LBP的视频文本检测算法[J].计算机工程,2011,37(18):174-176. 被引量:1
  • 9袁海东,马华东,黄晓冬.基于梯度与粗糙度的视频文本检测与定位[J].电子学报,2008,36(8):1660-1664. 被引量:9
  • 10王文震.基于流形学习的视频中文文本检测算法[J].科技通报,2012,28(10):46-48. 被引量:11

二级参考文献29

  • 1谢毓湘,栾悉道,吴玲达,老松杨.新闻视频帧中的字幕探测[J].计算机工程,2004,30(20):167-168. 被引量:15
  • 2高丽,杨树元,夏杰,王诗俊,梁军利,李海强.基于标记的Watershed图像分割新算法[J].电子学报,2006,34(11):2018-2023. 被引量:34
  • 3JIANG Ren-jie QI Fei-hu XU Li WU Guo-rong ZHU Kai-hua.A learning-based method to detect and segment text from scene images[J].Journal of Zhejiang University-Science A(Applied Physics & Engineering),2007,8(4):568-574. 被引量:3
  • 4Phan T Q, Shivakumara P, Tan C L. A Laplacian Method for Video Text Detection[C]//Proc. of IEEE ICDAR’09. [S. l.]: IEEE Press, 2009: 66-70.
  • 5Jun Ye, Huang Linlin, Hao Xiaoli. Neural Network Based Text Detection in Videos Using Local Binary Patterns[C]//Proc. of CJKPR’09. Nanjing, China: [s. n.], 2009: 916-920.
  • 6Wong E K, Chen Minya. A New Robust Algorithm for Video Text Extraction[J]. Pattern Recognition, 2003, 36(6): 1397- 1406.
  • 7Ye Qixiang, Huang Qingming, Gao Wen, et al. Fast and Gobust Text Detection in Images and Video Frames[J]. Image and Vision Computing, 2005, 23(6): 565-576.
  • 8Lee C W, Jung K, Kim H J. Automatic Text Detection and Removal in Video Sequences[J]. Pattern Recognition Letters, 2003, 24(15): 2607-2623.
  • 9Ojala T, Pietikainen M, Harwood D. A Comparative Study of Texture Measures with Classification Based on Feature Distributions[J]. Pattern Recognition, 1996, 29(1): 51-59.
  • 10Y K Lim, S H Choi, S W Lee. Text extraction in MPEG compressed video for content-based indexing[ A] .The 15th International Conference on Pattern Recognition [ C ]. Barcelona, Spain, 2000,4:409 - 412.

共引文献20

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部