Design of Surface defect Detection system for Tungsten Rod based on FPGA

Aiming at the tungsten bar surface defect detection in the production process relies on manual completion, identification of low efficiency, slow speed, labor intensity and other issues, this paper designs a set of tungsten bar surface defect detection system based on machine vision and FPGA hardware platform. The image collected by the image sensor by Gaussian filtering, gray scale conversion, median filtering, threshold segmentation, morphological processing to obtain the binarized feature map, and then use the pixel mutation algorithm to identify the tungsten rod surface defect features, and realize the FPGA hardware deployment. Finally, the experimental platform is built to experimentally verify the algorithm, and the experimental results show that: the system operates stably, the accuracy Ac reaches 92%, and the normal tungsten rod recognition F
NR
reaches 96%, which can be applied to the actual production to improve the production efficiency and reduce the production cost.