The Document Spectrum for Page Layout Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast orientation and skew detection algorithm for monochromatic document images
Proceedings of the 2005 ACM symposium on Document engineering
Computational Geometry: Algorithms and Applications
Computational Geometry: Algorithms and Applications
Performance Evaluation and Benchmarking of Six-Page Segmentation Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Two-Step Dewarping of Camera Document Images
DAS '08 Proceedings of the 2008 The Eighth IAPR International Workshop on Document Analysis Systems
Segmentation of Curled Textlines Using Active Contours
DAS '08 Proceedings of the 2008 The Eighth IAPR International Workshop on Document Analysis Systems
Ridges Based Curled Textline Region Detection from Grayscale Camera-Captured Document Images
CAIP '09 Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns
Coupled Snakelet Model for Curled Textline Segmentation of Camera-Captured Document Images
ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Textline information extraction from grayscale camera-captured document images
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Fast Construction of k-Nearest Neighbor Graphs for Point Clouds
IEEE Transactions on Visualization and Computer Graphics
Correcting book binding distortion in scanned documents
ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part II
A new method for text-line segmentation for warped documents
ICIAR'10 Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part II
| Hi-index | 0.00 |
The digitalization of bound documents either using flatbed scanners or digital cameras often yield images with non-straight text-lines due to a geometrical warp. This paper presents a new algorithm for text-line segmentation for documents captured by digital cameras or scanners. The proposed method reached 97.84% correct segmentation, while the best results offered by its predecessors in the literature yields 95.21%.