Three-Stage Method of Text Region Extraction from Diagram Raster Images
作者： Jerzy Sas , Andrzej Zolnierek
DOI: 10.1007/978-3-319-00969-8_52
关键词: Raster graphics 、 Computer vision 、 Diagram 、 Artificial intelligence 、 Three stage 、 Vector graphics 、 Computer science 、 Layer (object-oriented design) 、 Work in process 、 Combined approach
摘要: In the paper combined approach to problem of text region recognition is presented. We focused our attention on chosen case extraction from specific type images where imposed over graphical layer vector (charts, diagrams, etc.). For such we proposed three-stage method using OCR tools as some kind feed-back in process searching. Some experimental results and examples practical applications are also briefly described.
springer.com
sci-hub.st 参考文章(5)
Kongqiao Wang, Jari A. Kangas, Character location in scene images from digital camera Pattern Recognition. ,vol. 36, pp. 2287- 2299 ,(2003) , 10.1016/S0031-3203(03)00082-7
Victor Wu, R. Manmatha, Edward M. Riseman, Finding text in images acm international conference on digital libraries. pp. 3- 12 ,(1997) , 10.1145/263690.263766
U.-V. MARTI, H. BUNKE, Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition systems International Journal of Pattern Recognition and Artificial Intelligence. ,vol. 15, pp. 65- 90 ,(2001) , 10.1142/S0218001401000848
Boris Epshtein, Eyal Ofek, Yonatan Wexler, Detecting text in natural scenes with stroke width transform computer vision and pattern recognition. pp. 2963- 2970 ,(2010) , 10.1109/CVPR.2010.5540041
Xiaoqing Liu, Jagath Samarabandu, Multiscale Edge-Based Text Extraction from Complex Images international conference on multimedia and expo. pp. 1721- 1724 ,(2006) , 10.1109/ICME.2006.262882