An intelligent computer method for automatic mosaic and segmentation of tracer fiber images for yarn structure analysis

Abstract

Tracer fiber measurement is a popular and effective method to study yarn internal structure. In this method, a series of consecutive yarn images are stitched into panorama, and yarn boundaries and tracer fiber are extracted for further analysis. Currently, the image mosaic and segmentation of tracer fiber images largely involve manual operation because the existing image processing methods are generally not capable in most cases. Therefore, this study aims to develop an intelligent computer method for automatic mosaic and segmentation of tracer fiber images. In this study, an extended QRS complex detection method is developed for tracer fiber detection. In the image mosaic, a decision function, integrating several matching functions extracted from the tracer fiber and gradient image, is proposed to identify the optimal stitching position. The QRS complex is a name for the combination of Q wave, R wave and S wave on an electrocardiogram (ECG), which reflects the rapid depolarization of the right and left ventricles. In image segmentation, a baseline fitting method is used to eliminate the effect of uneven background for identifying yarn boundaries from the binary image. Finally, an objective method is proposed to evaluate the qualities of the image mosaic and segmentation of the proposed method.