Abstract
An effective perspective distortion correction method is presented to resolve the perspective distortion correction in text recognition of natural scene. A vanishing point is detected by text baseline obtained from the tip point of text character. A vanishing point position is used to get some deformation parameters of homography matrix, which is utilized to correct the image. The front view image is achieved using a homography matrix. Compared with other methods, this method is less restricted by text layout. Experimental results show this method can effectively correct the text image with a few lines in natural scene and increase recognition rate significantly.
| Original language | English |
|---|---|
| Pages (from-to) | 436-441 |
| Number of pages | 6 |
| Journal | Nanjing Li Gong Daxue Xuebao/Journal of Nanjing University of Science and Technology |
| Volume | 35 |
| Issue number | 4 |
| State | Published - Aug 2011 |
| Externally published | Yes |
Keywords
- Distortion correction
- Perspective distortion
- Scene texts
- Vanishing points
Fingerprint
Dive into the research topics of 'Perspective distortion correction method of scene text based on vanishing point'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver