Skew detection using wavelet decomposition and projection profile analysis
Pattern Recognition Letters
Hi-index | 0.00 |
In this paper, a novel fabric skew detection method based on DFT and multi-projection analysis is proposed. First, perform DFT for the fabric image, then use the image binaryzation which is to remove redundant information. Rotate the binary spectrum of the image from ---5° to +5° in small step. After each rotation, project the image to the transverse axis. Then detect the skew angle of the fabric image based on that a maximum of projection pixels appears in the center of the spectrum if the longitudinal centerline of the spectrum is vertical to the transverse axis. Experimental results show that this algorithm has high accuracy in detecting small amount of fabric skew and better adaptability of the fabric density.