A novel approach of skew estimation and correction in persian manuscript text using radon transform

Skew angle estimation is an important component of optical character recognition (OCR) systems. In this paper, a new optimizing method is introduced that is called “Finding the Skew with Radon (FSR)” in order to estimate the skew of the handwritten text. The above mentioned method has three stages. First of all, input text image is converted into a binary form and then the words and sub-words are became dilated. Then, the pattern angle is attained by using Radon transform. Finally, the inversion or non-inversion of the result image from the previous stage is recognized by extraction of horizontal histogram of that image and statistical analysis. To demonstrate the FSR method's outcomes, this proposed method is simulated for a complex of various Persian handwritten images, and then it is observed that its results in comparison with last methods are significantly optimized.