An improved FCM algorithm for glass defect extraction of mobile phone screen cover plate

Aiming at the problem that the defect extraction of mobile phone screen cover is easily disturbed by noise, a fuzzy C-means (FCM)clustering method based on wavelet transform and particle swarm improvement was proposed. Firstly, the collected mobile phone screen cover image is filtered by wavelet transform to reconstruct the image, and then the FCM algorithm is optimized by particle swarm optimization algorithm to update the clustering center globally, so as to avoid the shortcoming of local optimization of FCM algorithm. The experimental results show that the improved FCM algorithm based on wavelet transform and particle swarm optimization is better than other traditional methods in the detection of mobile phone screen cover defects, and its accuracy can reach 99.90%.