Abstract | ||
---|---|---|
Due to the huge amount of data carried by images, it is very important to detect and identify the text region as accurately as possible before performing any character recognition. In this paper we describe a text detection algorithm in complex background. It is based on texture and connected components analysis. First we abstract texture regions which usually contain text. Second, we segment the texture regions into suitable objects; the image is segmented into three classes. Finally, we analyze all connected components present in each binary image according to the three classes with the aim to remove non-text regions. Experiments on a benchmark database show the advantages of the new proposed method compared to another one. Especially, our method is insensitive to complex background, font size and color; and offers high precision (83%) and recall(73%) as well. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-13681-8_19 | ICISP |
Keywords | Field | DocType |
texture region,text detection algorithm,connected components analysis,benchmark database,text region,abstract texture region,complex background,geometric feature,binary image,connected component,new approach,new proposed method,feature extraction,geometric analysis | Computer vision,Point (typography),Pattern recognition,Character recognition,Computer science,Image texture,Binary image,Geometric analysis,Feature extraction,Artificial intelligence,Connected component,Text detection | Conference |
Volume | ISSN | ISBN |
6134 | 0302-9743 | 3-642-13680-X |
Citations | PageRank | References |
0 | 0.34 | 13 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hinde Anoual | 1 | 0 | 0.68 |
Sanaa El Fkihi | 2 | 10 | 7.52 |
Abdelilah Jilbab | 3 | 8 | 3.07 |
Driss Aboutajdine | 4 | 589 | 88.82 |