To recognize the abnormal heating of cable terminal, Radon and Fourier-Mellin transform is used to extract the feature in the paper. First, processing the original image by Radon transform and Fourier-Mellin transform successively and then extracting the four feature quantities of the transformed image based on invariant function. Finally, feature vectors will be input to the BP neural network for image recognition. It can be concluded from the result that the method proposed in the paper can reflect features of the infrared image more effectively. Infrared image with Pepper and salt noise and white Gaussian noise is recognized based on the method which proves its strong robusticity on noise disturbance.