Evaluation of insulator operation is important for safely operating transmission lines. Ultraviolet (UV) imaging is a quantitative method for evaluating insulators. Therefore, a UV spot area assessment method based on an improved ANFIS for insulators was proposed. First, an insulator pollution discharge test platform was built to study the discharge intensity of the insulators at different test distances and gains. Second, an ANFIS(adaptive neuro-fuzzy inference system) model based on Bayesian inference is established using the gain and ultraviolet spot area as training data. Finally, a field verification test was conducted. The results show that this method has good prediction accuracy and test efficiency and is suitable for the quantitative evaluation of ultraviolet imaging for insulators, which provides technical support for the evaluation of the operating state of insulators.