Improved Skew Detection and Correction Approach Using Discrete Fourier Algorithm

The main objective of Image processing is to convert an image into digital form and perform some operations on it, in order to get an enhanced image or to extract some useful information from it. But when they are needed to be converted into electronic form, it has to be done through scanning. One of the major problems in this field is that if the document to be read is not placed at 90. This will result with a skewed image. Skew refers to the text which neither parallel nor at right angles to a specified or implied line. Character recognition is very sensitive to the page skew, skew detection and correction in document images are the critical steps before ayout analysis. To achieve the objective of Skew detection and correction, a new improved strategy is proposed which uses the Fourier transformation and angle of elevation theory to detect the skewness angle first and then skew correction algorithm will come in action. As Fourier transform will speed up the algorithm so speed no longer is an issue for proposed algorithm. Also angle of elevation theory has ability to detect angle in efficient manner. Proposed algorithm is designed and implemented in Matrix Laboratory by taking a sample of 120 different Skewed images. These images include documents having different languages: English, Hindi, Punjabi and Pictures. Keywords—Skew detection, Fast Fourier transform, Discrete Fourier transform, Radon transform, Moments.