yildiz, kazım marmara university - technology faculty - department of computer engineering, Istanbul, Turkey , demir, önder marmara university - technology faculty - department of computer engineering, Istanbul, Turkey , ülkü, eyüp emre marmara university - technology faculty - department of computer engineering, Istanbul, Turkey

Görüntü işleme yöntemleri kullanarak kumaş dokularında hata tespiti

40992

This paper presents a computer aided detection (CAD) system which uses wiener filter based approach for detection of defects in poplin fabric. The defective fabric images are taken with the help of the digital camera. The developed system consists of three phases, including preprocessing, segmentation and detection of fabric defect. In preprocessing phase, a RGB to gray level conversion and image enhancement operations were applied to digital camera images. In segmentation phase, background of the gray level image segmented using morphologic operations. Then, segmented image was converted to binary image to facilitate fabric defect detection process. Fabric defect detection was performed using wiener filter in the detection phase of the system. Wiener filter is applied to binary level image to eliminate structures which are not defect. The developed detection system applied on defective poplin images for detection. The obtained results on different kinds of fabric defects show that the proposed algorithm gives promising results.

841

Texture surface , Defect detection , Wiener filter , Computer aided detection , Segmentation

Pamukkale University Journal Of Engineering Sciences

844