Automated Density Measurement of Weft Knitted Fabrics Using Backlight Imaging

Abstract

This paper proposes a new density measurement algorithm to address the issues of poor applicability and inaccurate results associated with the automatic density measurement algorithm for weft-knitted fabrics. The algorithm involves collecting the transmitted light image of the knitted fabric, calculating the tilt angle using the skewing correction algorithm, and rotating the image to correct the weft skew present therein. The pre-rotated and post-rotated images are then projected vertically and horizontally in grayscale, and the obtained projection curves are used to represent the distribution of loops in vertical and horizontal rows. This study proposed a wave peak coordinate verification algorithm that calculates the coursewise densities and walewise densities of the knitted fabric. In experiments, the proposed density measurement method is found to exhibit an accuracy above 98% when compared with the manual mode.