A Complete Tamil Optical Character Recognition System
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
Skew detection and correction in document images based on straight-line fitting
Pattern Recognition Letters
A nearest-neighbor chain based approach to skew estimation in document images
Pattern Recognition Letters
Document Image Retrieval Based on Density Distribution Feature and Key Block Feature
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Skew detection using wavelet decomposition and projection profile analysis
Pattern Recognition Letters
Pattern Recognition Letters
A fast skew detection and correction algorithm for machine printed words in Gurmukhi script
Proceedings of the International Workshop on Multilingual OCR
Document skew estimation: an approach based on wavelets
Proceedings of the 2011 International Conference on Communication, Computing & Security
Hi-index | 0.00 |
A fast and robust skew detection algorithm for grayscale image is presented in this paper. This MCCSD (Modified Cross-Correlation Skew Detection) algorithm use horizontal and vertical cross-correlation simultaneously to deal with vertical layout text which is commonly used in Chinese or Japanese document. Instead of calculating correlation for the entire image, we use randomly selected small regions to speed up the process. Region verification stage and auxiliary peaks further processing make our method robust and reliable. Experiment shows that proposed method has good result on detecting skew in various kinds of pages.