Patent
Skew detection in document images
Laurent Alain Najman
- pp 16
Reads0
Chats0
TLDR
In this article, the authors estimate the skew angle in a document image (A) by smoothing the image and then producing a plurality of eroded run-length-smoothed images.Abstract:
of EP1394725Skew angle in a document image (A) is estimated using operators known from mathematical morphology. Skew angle in a document image (A) is estimated by run-length smoothing the image and then producing a plurality of eroded run-length-smoothed images. The run-length-smoothed image (RLSA(A)) is eroded using a linear structuring element (k2L alpha ) oriented at each of a plurality of different angles ( alpha ). The angle of the linear structuring element which produces an eroded image having the greatest surface area is designated as the skew angle. A plurality of run-length-smoothed images (RLSA alpha (A)) may be produced, each generated by smoothing the document image using a linear structuring element (k1L alpha ) oriented at a respective different angle ( alpha i). Then each run-length smoothed image (RLSA alpha (A)) is eroded using a linear structuring element oriented at the corresponding angle ( alpha i).read more
Citations
More filters
Patent
Document image slant angle estimation method based on content
Ma Lei,Liu Jiang,Chen Xia +2 more
TL;DR: In this paper, a document image slant angle estimation method based on content is proposed, where the linear segment or the text line is used to estimate the slant angles of the document image.
References
More filters
Proceedings ArticleDOI
A rule-based system for document image segmentation
TL;DR: A rule-based system for automatically segmenting a document image into regions of text and nontext is presented and allows easy fine tuning of the algorithmic steps to produce robust rules, to incorporate additional tools (as they become available), and to handle special segmentation needs.
Proceedings ArticleDOI
An automatic algorithm for text skew estimation in document images using recursive morphological transforms
Su Chen,Robert M. Haralick +1 more
TL;DR: Methodology is developed to allow the algorithm to determine the optimal algorithm parameter settings on the fly without any human interaction and results indicate that the algorithm generates estimated text skew angles which are within 0.5/spl deg/ of the true text skew angle 99% of the time.
Journal ArticleDOI
A fast algorithm for skew detection of document images using morphology
Amit Kumar Das,Bhabatosh Chanda +1 more
TL;DR: A new method for automatic detection of skew in a document image using mathematical morphology is presented, which is extremely fast as well as independent of script forms.
Proceedings ArticleDOI
Applying fast segmentation techniques at a binary image represented by a set of non-overlapping blocks
B. Gatos,N. Papamarkos +1 more
TL;DR: This paper shows that starting from a block represented binary image the authors can apply RLSA and evaluate projection profiles in significant less CPU time and the average time gain is recorded at 60% and 88%, respectively.