Text extraction in document images: highlight on using corner points

被引:10
作者
Yadav, Vikas [1 ]
Ragot, Nicolas [2 ]
机构
[1] Visvesvaraya Natl Inst Technol, ECE Dept, Nagpur, Maharashtra, India
[2] Univ Francois Rabelais Tours, Lab Informat LI EA6300, Tours, France
来源
PROCEEDINGS OF 12TH IAPR WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS, (DAS 2016) | 2016年
关键词
text extraction; corner points; FAST (Features from Accelerated Segment Test); multilingual documents; historical documents; handwritten documents;
D O I
10.1109/DAS.2016.67
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
During past years, text extraction in document images has been widely studied in the general context of Document Image Analysis (DIA) and especially in the framework of layout analysis. Many existing techniques rely on complex processes based on preprocessing, image transforms or component/edges extraction and their analysis. At the same time, text extraction inside videos has received an increased interest and the use of corner or key points has been proven to be very effective. Because it is noteworthy to notice that very few studies were performed on the use of corner points for text extraction in document images, we propose in this paper to evaluate the possibilities associated with this kind of approach for DIA. To do that, we designed a very simple technique based on FAST key points. A first stage divide the image into blocks and the density of points inside each one is computed. The more dense ones are kept as text blocks. Then, connectivity of blocks is checked to group them and to obtain complete text blocks. This technique has been evaluated on different kind of images: different languages (Telugu, Arabic, French), handwritten as well as typewritten, skewed documents, images at different resolution and with different kind and amount of noises (deformations, ink dot, bleed through, acquisition (blur, resolution)), etc. Even with fixed parameters for all such kind of documents images, the precision and recall are close or higher to 90% which makes this basic method already effective. Consequently, even if the proposed approach does not propose a breakthrough from theoretical aspects, it highlights that accurate text extraction could be achieved without complex approach. Moreover, this approach could also be easily improved to be more precise, robust and useful for more complex layout analysis.
引用
收藏
页码:281 / 286
页数:6
相关论文
共 37 条
[1]  
[Anonymous], 2015, P IMECHE J
[2]  
Antonacopoulos A., 2013, 12 INT C DOC AB REC
[3]  
Antonacopoulos A., 2009, 10 C DOC AN REC
[4]  
Audithan S., 2009, EUROPEAN J SCI RES, V36, P502
[5]  
Boussellaa Wafa, 2009, 2009 10th International Conference on Document Analysis and Recognition (ICDAR), P743, DOI 10.1109/ICDAR.2009.220
[6]   TEXTLINE INFORMATION EXTRACTION FROM GRAYSCALE CAMERA-CAPTURED DOCUMENT IMAGES [J].
Bukhari, Syed Saqib ;
Breuel, Thomas M. ;
Shafait, Faisal .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :2013-+
[7]  
Chaudhuri A.R., 2002, P LANG ENG C
[8]  
Chen YL, 2012, INT J INNOV COMPUT I, V8, P303
[9]  
Doermann D, 2014, Handbook of Document Image Processing and Recognition
[10]  
Fanfeng Zeng, 2013, Journal of Software, V8, P1827, DOI 10.4304/jsw.8.8.1827-1834