Intelligent recognition of the patterns of yarn-dyed fabric based on LSRT images

Abstract

In this article, an intelligent inspection method based on image analysis is proposed to identify the color and woven pattern of yarn-dyed fabric automatically. The local sequence images under the reflected light and transmitted light (LSRT images), which consist of reflection sequence images and transmission sequence images, are first captured by a fabric image acquisition device. Then the Fourier transform, image segmentation, and arithmetic operations are employed to the transmission sequence images to determine the location of weave points. Subsequently, the L*a*b* values of each weave point are extracted from the reflection sequence images. To inspect the color pattern, X-means clustering algorithm is used to classify the weave points based on the L*a*b* values. To detect the woven pattern, incomplete weave pattern matrixes of all sequence images are used to match the weave pattern database. Eight LSRT images of each yarn-dyed fabric sample are tested by the proposed method. The experimental results proved that the proposed method can recognize the color and weave pattern of yarn-dyed fabric with satisfactory accuracy and good robustness.