Particle Swarm Optimization Enabled Filtering For Fabric Images in Automated Fabric Inspection System

摘要

Random variations in intensity, poor contrast, variations in illumination are the common reasons for the images to be usually corrupted. These corruptions must be handled by the early stages of vision processing. Even though there are wide varieties of filtering techniques available for the purpose of removing noise in digital images, the problem still remains challenging in research. This paper shows how, Particle Swarm Optimization (PSO) enabled filtering method has been implemented and its performance is compared with the other filtering techniques such as Median, Gaussian filtering methods. The performances of these filtering methods on digital fabric images are assessed based on the metrics Mean squared error (MSE) and Peak signal to noise ratio (PSNR). The implementation results are then compared and evaluated.