The hydrophobic detection of composite insulators is an important means to ensure the safe and reliable op-eration of insulators. The effective elimination of noise from hydrophobic images is an important prerequisite for accu-rately extracting the edge of water droplets and realizing the hydrophobic identification of insulators. The guiding fil-tering algorithm is widely applied in the field of image processing because of its intuitive principle, low computationalcomplexity and its ability to effectively overcome the gradient inversion problem by the guiding image filtering. In thiscontext, the principle of guided filtering is analyzed firstly. Then, it is introduced into the denoising process of hydro-phobic image based on the image characteristics. Finally, the results of filtering experiment and quantitative experi-ment are analyzed to verify the good effect of the guided filtering algorithm in the preprocessing of hydrophobic imageedge extraction.