DocumentCode :
248373
Title :
Pixel Probability Based Estimation of Skew Angle for Text Images
Author :
Wajid, Mohd ; Goel, Abhilasha Rani
Author_Institution :
Dept. of ECE, Jaypee Univ. of Inf. Technol., Solan, India
fYear :
2014
fDate :
27-29 Aug. 2014
Firstpage :
105
Lastpage :
108
Abstract :
The document reader reads the data from text document image for optical character recognition. If the image is rotated, it will not work properly. Some document images have a few degree of skew angle which creates difficulties in many other applications, so it is necessary to find out the skew angle of the digitalized document. This paper proposed an algorithm to automatically determine the skew angle of a text document image and produce a de-skewed image. The algorithm is based on the ratio of probability of the two binary pixels with the fact that rotated image matrix has higher order as compared to original image matrix and the ratio of probability of black pixels and white pixels changes. The algorithm is tested on more than 525 images taken from the IAM handwriting database [9] and on images generated by our self, for skew angle from -45° to +45° with 0.1° angle increment and found good angle estimation with mean error -0.0667° and variance = 1.3165°.
Keywords :
document image processing; optical character recognition; probability; visual databases; IAM handwriting database; binary pixels; black pixels; document reader; optical character recognition; pixel probability based estimation; rotated image matrix; skew angle estimation; text document image; white pixels; Character recognition; Clocks; Databases; Estimation; Image edge detection; Matrix converters; Optical character recognition software; OCR (optical character recognition); Skew estimation; rotation transform;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advances in Computing and Communications (ICACC), 2014 Fourth International Conference on
Conference_Location :
Cochin
Print_ISBN :
978-1-4799-4364-7
Type :
conf
DOI :
10.1109/ICACC.2014.31
Filename :
6906000
Link To Document :
بازگشت