Insulators are important equipment on the transmission line. if fault occurs, it will bring huge loss to power equipments. Locating and extracting insulator from infrared image of transmission line can basically reflect a variety of insulator faults, which is more practical in insulator identification and fault diagnosis.This paper proposes an insulator recognition method based on infrared images, which sequentially use the Speeded Up Robust Features (SURF) algorithm to extract the key feature points of the test infrared images, cluster the feature points based on the improved Fuzzy C-means (FCM) algorithm, identify and locate the insulators according to the shape feature values of the insulators and precise extraction of insulators based on improved image opening operation. This method makes full use of the advantages of infrared images and can accurately extract insulators, which lays a foundation for insulator fault diagnosis based on infrared images.