Skew Detection and Correction Method of Fabric Images Based on Hough Transform

Abstract

To solve the skew situation of scanned fabric image, a method based on Hough transform for skew detection and correction in fabric images was presented. By combining the characteristics of fabric images and the weft direction information extracted by Sobel operator, this method performed hierarchical Hough transform on the weft boundary to detect the skew angle of fabric image. Finally, a rotation algorithm based on the image linear storage structure was introduced, and the skew image was corrected rapidly. The skew detect algorithm has been experimented on various skew angles of fabric image and very promising results have been achieved given more than 99% accuracy. Experimental results show that the proposed method with high adaptability is more accurate and rapidly than traditional Hough transform.