Shivakumara, P. and Kumar, G. H. and Guru, D. S. and Nagabhushan, P. (2004) An efficient skew estimation technique for binary document images based on boundary growing and linear regression analysis. In: NEURAL INFORMATION PROCESSING.
Full text not available from this repository.Abstract
Skew angle estimation is an important component of an Optical Character Recognition (OCR) and Document Analysis Systems (DAS). In this paper, a novel and efficient (in terms of accuracy and computations) method to estimate skew angle of a scanned document image is proposed. The proposed technique works based on fixing a boundary for connected components and growing boundaries. The technique uses Linear Regression Analysis to estimate skew angles. However, the technique works based on the assumption that the space between the two adjacent text lines is greater than the space between the successive characters present in a text line. The proposed method is compared with other existing methods. The experimental results are also presented.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Additional Information: | 11th International Conference on Neural Information Processing, Calcutta, INDIA, NOV 22-25, 2004 |
| Subjects: | D Physical Science > Computer Science |
| Divisions: | Department of > Computer Science |
| Depositing User: | Users 23 not found. |
| Date Deposited: | 20 Aug 2019 12:27 |
| Last Modified: | 20 Aug 2019 12:27 |
| URI: | http://eprints.uni-mysore.ac.in/id/eprint/6647 |
Actions (login required)
 |
View Item |
