Skew correction of document images using interline cross-correlation
CVGIP: Graphical Models and Image Processing
The skew angle of printed documents
Document image analysis
An improved document skew angle estimation technique
Pattern Recognition Letters
A fast approach to the detection and correction of skew documents
Pattern Recognition Letters
The Document Spectrum for Page Layout Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Skew Detection of Document Images by Focused Nearest-Neighbor Clustering
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Robust detection of skew in document images
IEEE Transactions on Image Processing
A fast skew detection and correction algorithm for machine printed words in Gurmukhi script
Proceedings of the International Workshop on Multilingual OCR
Fast and robust skew estimation of scanned documents through background area information
Pattern Recognition Letters
A new approach for instance-based skew estimation
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part IV
| Hi-index | 0.00 |
The nearest-neighbor based document skew detectionmethods do not require the presence of a predominanttext area, and are not subject to skew angle limitation.However, the accuracy of these methods is not perfectin general. In this paper, we present an improvednearest-neighbor based approach to perform accuratedocument skew estimation. Size restriction is introduced tothe detection of nearest-neighbor pairs. Then the chainswith a largest possible number of nearest-neighbor pairsare selected, and their slopes are computed to give the skewangle of document image. Experimental results on varioustypes of documents containing different linguistic scriptsand diverse layouts show that the proposed approach hasachieved an improved accuracy for estimating documentimage skew angle and has an advantage of being languageindependent.