Abstract: The continuous change of the wall thickness for the lap joint workpiece brings about the very different gray levels in X-ray background image. So it is difficult to automatically recognize defects using digital image processing method in X-ray image. In this paper,a method based on X-ray background image removal was presented to solve the problem above mentioned. Firstly,image noise suppression is carried on using Wavelet. Secondly,according to the X-ray image character,background image is calculated. And using the designed background image,the front image can be obtained. Then the front image is segmented using iterative threshold method. At last mathematical morphology based image processing method is carried on. The results show that the proposed method can automatically recognize the gas pores in single lap joint.