Abstract: The insulator is easy to result in self-shattering fault if exposed in the natural environment for long time.For this situation,this paper presented an image processing method for insulator defect detection and location.Based on the pattern characteristics of insulator in aerial image,the between-cluster variance method and median filtering were used to preprocess the image.The ant colony algorithm with optimized parameters obtained by particle swarm optimization algorithm was proposed to detect the contour and number of insulator in the aerial image.At last,the location of defective insulator was marked in the original image.This method has good effect for defective insulator detection under simple background,and establishes pre-research foundation to realize insulator defect detection and localization under complex background.

Key words: Between-cluster variance method,Particle swarm optimization algorithm,Ant colony algorithm,Insulator defect detection and location