Title :
Fabric defect detection based on open source computer vision library OpenCV
Author_Institution :
Coll. of Math. & Inf. Eng., Jiaxing Univ., Jiaxing, China
Abstract :
A method for fabric defect detection based on OpenCV with rich computer vision and image processing algorithms and functions is presented. Firstly, OpenCV image processing functions implement fabric image preprocessing. We use morphological opening and closing operations to segment image because of their blur defects. Secondly, “seed filling” algorithm is applied to connect broke lines to keep defect edge smoothing. Finally, the edge detection function is to complete accurate positioning defects. Experimental results under Borland C++ Builder 6.0 show that OpenCV based fabric defect detection methods are simple, high code integration, accurate defects positioning, which can be applied to develop real-time fabric defect detection system.
Keywords :
C++ language; computer vision; edge detection; fabrics; production engineering computing; public domain software; Borland C++ Builder 6.0; OpenCV; edge detection function; fabric defect detection; image processing algorithms; image segmentation; morphological closing operation; morphological opening operation; open source computer vision library; seed filling algorithm; Computer vision; Fabrics; Image segmentation; Libraries; Pixel; Signal processing algorithms; OpenCV; fabric defect; image processing; morphology;
Conference_Titel :
Signal Processing Systems (ICSPS), 2010 2nd International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4244-6892-8
Electronic_ISBN :
978-1-4244-6893-5
DOI :
10.1109/ICSPS.2010.5555633
