Halil İbrahim Çelik

Development of a machine vision system: real-time fabric defect detection and classification with neural networks

In this study, a machine vision system is developed to achieve fabric inspection and defect classification processes automatically. The system consists of an image acquisition hardware and an image processing software. A simple and portable system was designed so that it can be adapted easily to all types of the fabric inspection machines. The software of the system consists of defect detection and classification algorithms. The defect detection algorithm is based on wavelet transform, double thresholding binarization, and morphological operations. It was applied real time via a user interface prepared by using MATLAB® program. The defect classification approach is based on gray level co-occurrence matrix and feed forward neural network. Five commonly occurring defect types, warp lacking, weft lacking, soiled yarn hole, and yarn flow, were detected and classified. The defective and defect-free regions of the fabric were detected with an accuracy of 93.4% and the defects are classified with 96.3% accuracy rate.

Real-Time Denim Fabric Inspection Using Image Analysis

In spite of using modern weaving technology, many types of fabric defects occur during production. Most defects arising in the production process of a fabric are still detected by human inspection. A machine vision system that can be adapted to different types of fabric inspection machines is proposed in this study. Image frames of denim fabric were acquired using a CCD line-scan camera. An algorithm was developed by using the Gabor filter and double thresholding methods. The performance of the algorithm was tested real-time by analysing a denim fabric sample which contained six types of defects: hole, warp lacking, weft lacking, soiled yarn, water soil and yarn flow (knot). The defective regions of the denim fabric sample were detected and labelled successfully.

Kinematic analysis and synthesis of the beat‐up mechanism for handmade carpet looms

The beat‐up process has a great influence on the structure and appearance of the handmade carpet. Since all weaving processes of the handmade carpet are performed by the weaver, the production speed may be increased and the performance of the weaver may be improved by designing a suitable beat‐up mechanism. In this article, a crank‐rocker type of four‐bar mechanism has been studied for the handmade carpet loom beat‐up mechanism. First, the functional requirements of the beat‐up mechanism were established according to the problem statement. Later, a four‐bar crank‐rocker‐type mechanism was generated and developed from a slider‐crank‐type mechanism. Here, the dimensional synthesis of the mechanism was made as a solution to the slider‐crank‐type mechanism. Many alternative mechanisms were generated as a result of the dimensional synthesis. The slider‐crank‐type mechanisms were then translated into the crank‐rocker‐type mechanisms. These mechanisms were evaluated in terms of some mechanical criteria and the most suitable one was selected. Finally, a kinematic analysis of the beat‐up mechanism was performed.

Thermophysiological comfort and performance properties of knitted fabrics produced from different spinning technologies

Abstract In this study, it was intended to investigate the effects of yarn spinning technology on knitted fabric thermophysiological comfort and performance properties. For this aim, three different 100% cotton Ne 16/1 yarn samples were produced with different spinning technologies namely, combed ring, compact and sirospun. Then six knitted fabric samples were produced with two different loop lengths. In the context of this study, air permeability and water vapour permeability tests were done as thermophysiological comfort tests, pilling resistance and abrasion resistance tests were performed as performance tests. In order to understand the statistical importance of spinning technology and loop length on knitted fabric properties, ANOVA was performed. According to the results, it is seen that spinning technology and loop length have important effects on observed properties.

Effect of fiber blending ratios of cotton/polyester yarns on retained splice diameter

The most important performance parameters of splicing are obtaining adequate strength and appearance at the splice point for all processing requirements. The diameter of spliced portion effects not only appearance of the splice joints but also physical characteristics such as packing density, strength, specific volume of the yarn. In this study, the effect of cotton/polyester fiber blend ratios on spliced portion diameter at different slicing air pressures was investigated. For this aim, three yarn samples 100% cotton, 80-20% CO-PES and 50- 50% CO-PES were produced with 40/1 Ne. Each yarn samples was spliced at three different pressures; 4 bar, 5 bar and 6 bar. The diameters of spliced portion and retained yarns were measured by using ImageJ program and the results were analyzed statistically.

Ayırma Tipi Mikrofilament İpliklerden Üretilmiş Örme Kumaşların Performans Özelliklerinin İncelenmesi

Ayirma tipi mikrofilamentler onemli bir mikrolif cesididir. Bu calisma kapsaminda, ayirma tipi mikrofilamentlerden uretilmisxa0 suprem orgu kumaslarin ayirma islemi oncesinde ve sonrasindaki performans ozellikleri arastirilmistir. Bu amacla, uc farkli kumasxa0 sikliginda (gevsek, orta, siki), suprem yapisinda uc orgu kumas numunesi uretilmis ve her birisinin yarisi ayirma islemine tabixa0 tutulmustur. Boylelikle, alti kumas numunesi elde edilmistir. Numunelerin hava gecirgenligi, su buhari gecirgenligi ve patlamaxa0 mukavemeti performanslari test edilmistir. Bu sekilde, farkli kumas sikliklai icin, konvansiyonel filamentlerden (ayirma islemixa0 oncesi) uretilmis orgu kumaslarla mikrofilamentlerden (ayirma islemi sonrasi) uretilmis orgu kumaslarin performans ozelliklerixa0 uzerine karsilastirmali bir calismanin yapilmasi amaclanmistir. Filament cesidinin ve kumas sikliginin orgu kumas performansinaxa0 etkisini istatistiksel olarak incelemek amaciyla iki yonlu ANOVA yapilmistir.