![]() | Only 14 pages are availabe for public view |
Abstract Seam Pucker is one of the most frequently occurring defects in garment industry. It is due to wide range of factors including fabric properties, sewing thread properties and sewing machine parameters. These factors separately or interacted affect the seam pucker grade. Many studies have been made on factors affecting seam pucker ~ but in the area of subjective evaluation and grading using the AATCC 88-B reference images. However, in the area of objective evaluation using image processing very little have been published. In the present work, seam pucker grade is tested on open seams resembling normal conditions of industrial inspection. Seam assemblies are prepared according to a three level experimental design changing six factors affecting seam pucker, namely: Fabric type, sewing machine speed, sewing thread, needle size, teeth height, and presser foot pressure. Image acquisition module obtains the digitized image of the seam assembly and stores it as a Bmp format in a computer file. Texture features are analyzed statistically. Three main computer programs are used on Matlab Version 5.3.. for identifying fabric type and color, extracting the first order statistical features £Tom the digitized images and extracting the second order statistical texture features. Fast Fourier Transform (FFT) and Discrete Cosine Transform (DCT) were also used for testing seam pucker grading. AATCC (American Association Textile Chemist and Colorist) seam pucker reference images are stored in the computer and delt with in the same way in order to set numbers for grading through comparing and quantifying grade. Fabric Type, sewing machine speed, teeth height and presser foot height are the main factors affecting the seam pucker grade. First order statistical features analysis showed better results than second order one. DCT transform showed better results than FFT for grading seam pucker. |