SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS
| Autor: | BRAD Raluca, H Ă LOIU Eugen, BRAD Remus |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: | |
| Zdroj: | Annals of the University of Oradea: Fascicle of Textiles, Leatherwork, Vol XV, Iss 1, Pp 23-28 (2014) |
| Druh dokumentu: | article |
| ISSN: | 1843-813X 70029083 |
| Popis: | 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). The puckering features presented in the learning and test images have been pre-classified using the seam puckering quality standard. The network training stage will consist in presenting five input vectors (derived from the down-sampled arrays), representing the puckering grades. The puckering classification consists in providing an input vector derived from the image supposed to be classified. A scalar product between the input values vectors and the weighted training images is computed. The result will be assigned to one of the five classes of which the input image belongs. Using the Kohonen network the puckering defects were correctly classified in proportion of 71.42%. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|