Seam Puckering Objective Evaluation Method for Sewing Process

TL;DR

This paper introduces an automated, image processing-based method for evaluating sewing puckering defects, reducing subjective bias and improving classification accuracy during preproduction inspections.

Contribution

It presents a novel automated system combining spectral image analysis and neural networks to classify puckering severity objectively.

Findings

Effective classification of puckering into five quality grades

Reduction of subjective assessment variability

Implementation of Fourier transform and Kohonen Map in defect evaluation

Abstract

The paper presents an automated method for the assessment and classification of puckering defects detected during the preproduction control stage of the sewing machine or product inspection. In this respect, we have presented the possible causes and remedies of the wrinkle nonconformities. Subjective factors related to the control environment and operators during the seams evaluation can be reduced using an automated system whose operation is based on image processing. Our implementation involves spectral image analysis using Fourier transform and an unsupervised neural network, the Kohonen Map, employed to classify material specimens, the input images, into five discrete degrees of quality, from grade 5 (best) to grade 1 (the worst).