Abstract This paper investigates on time-frequency image processing technology, which is used to improve practicality on rolling bearing fault diagnosis. Hough transform is used on Wigner-Ville time-frequency distribution analysis which can improve the accuracy of nonstationary signal analysis, especially for linear frequency modulation signal investigation. Different rolling bearing conditions pattern recognition is used as an example to testify the effectiveness of this method. According to result analysis of pattern recongtion, Hough transform for time-frequency image can effectively classify different rolling bearing fault.