Evaluation of an Intelligent Computer Method for the Automatic Mosaic of Sequential Slub Yarn Images

Abstract

This paper is the second part of a series reporting the recent development of a computerised method for automatic mosaic sequential yarn images. In our earlier work, an effective method for stitching sequence slub yarn images automatically was developed based on image processing and the normalised cross correlation (NCC) method. 100 image pairs of two kinds of slub yarn were measured in certain specific conditions, such as the frame rate, size of stitching template, etc., and the measurement results were evaluated with the manual method. In this paper, the effects of various influencing factors are numerically examined, including the stitching template size, threshold value, frame rate, and computing time of the mosaic algorithm. The feasibility and accuracy of the fully computerized method were evaluated further under the various influencing parameters. One hundred percent cotton ring spun single slub yarns of 27.8, 15.6, and 9.7 tex were prepared and used for the evaluation. The measurement results obtained by the method proposed are analysed and compared with those measured manually by Adobe Photoshop. The experimental results show that the method proposed can accurately find the stitch position and has a high consistency with the manual method when the matching template is 100 × N pixels, the threshold value T1 ∈ [20, 40] and T2 ∈ [51, 80], and the frame rate is greater than 40 fps.