SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS
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. Subjectiv...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editura Universităţii din Oradea
2014-07-01
|
| Series: | Annals of the University of Oradea: Fascicle of Textiles, Leatherwork |
| Subjects: | |
| Online Access: | http://textile.webhost.uoradea.ro/Annals/Vol%20XV-no%20I/Art.%20nr.%205,%20pag%2023-28.pdf |
| _version_ | 1818701484988039168 |
|---|---|
| author | BRAD Raluca H Ă LOIU Eugen BRAD Remus |
| author_facet | BRAD Raluca H Ă LOIU Eugen BRAD Remus |
| author_sort | BRAD Raluca |
| collection | DOAJ |
| description | 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%. |
| first_indexed | 2024-12-17T15:21:35Z |
| format | Article |
| id | doaj.art-36e19a65763d4501871d70029083b521 |
| institution | Directory Open Access Journal |
| issn | 1843-813X 1843-813X |
| language | English |
| last_indexed | 2024-12-17T15:21:35Z |
| publishDate | 2014-07-01 |
| publisher | Editura Universităţii din Oradea |
| record_format | Article |
| series | Annals of the University of Oradea: Fascicle of Textiles, Leatherwork |
| spelling | doaj.art-36e19a65763d4501871d70029083b5212022-12-21T21:43:23ZengEditura Universităţii din OradeaAnnals of the University of Oradea: Fascicle of Textiles, Leatherwork1843-813X1843-813X2014-07-01XV12328SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESSBRAD Raluca0H Ă LOIU Eugen1BRAD Remus2Lucian Blaga University of Sibiu, Romania, Departme nt of Industrial Machinery and Equipment, Faculty o f Engineering, B-dul Victoriei 10, 550024 Sibiu, Roma nia Information Multimedia Communication Sibiu, Str. N icolaus Olahus, Nr. 5, Sibiu, RomaniaLucian Blaga University of Sibiu, Romania, Departme nt of Computer Science and Electrical Engineering, Faculty of Engineering, B-dul Victoriei 10, 550024 Sibiu, RomaniaThe 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%.http://textile.webhost.uoradea.ro/Annals/Vol%20XV-no%20I/Art.%20nr.%205,%20pag%2023-28.pdfseamspuckerimage processingneural networkDiscrete Fourier Transform |
| spellingShingle | BRAD Raluca H Ă LOIU Eugen BRAD Remus SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS Annals of the University of Oradea: Fascicle of Textiles, Leatherwork seams pucker image processing neural network Discrete Fourier Transform |
| title | SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS |
| title_full | SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS |
| title_fullStr | SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS |
| title_full_unstemmed | SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS |
| title_short | SEAM PUCKERING EVALUATION METHOD FOR SEWING PROCESS |
| title_sort | seam puckering evaluation method for sewing process |
| topic | seams pucker image processing neural network Discrete Fourier Transform |
| url | http://textile.webhost.uoradea.ro/Annals/Vol%20XV-no%20I/Art.%20nr.%205,%20pag%2023-28.pdf |
| work_keys_str_mv | AT bradraluca seampuckeringevaluationmethodforsewingprocess AT haloiueugen seampuckeringevaluationmethodforsewingprocess AT bradremus seampuckeringevaluationmethodforsewingprocess |