A vision-based inspection system to measure woven fabric yarn densities during production is presented. As an extension to an earlier developed fabric flaw detection system, the proposed framework consists of a combination of basic and custom-made image processing techniques that allow to precisely track single wefts and warps within fabric images. Several adaptations allow the measurement of density changes for plain, satin and twill weaves. Only 3 parameters are required to set up the system, which can easily be obtained using any common photo processing software. The algorithmic framework has been evaluated in this work on a real-world loom and it proved to be robust and applicable for industrial use.
展开▼