Image inpainting is one of an activate resear ch topic in the domain of computer vision and computer graphics.Aiming at the pr oblem that the traditional crack image restoration method using one-time completion restoration method does not have the ability t o understand semantics,and the repair effect is not good when the semantic scene is more complex and the image defect is large,a crack image restoration based on progre ssive feature reasoning is proposed.This method gradually restores the image from the hole edge and strengthens the constraint on the hole center.At first,partial convolution i s used to update the mask,and the update ratio is determined by calculating the mask prop ortion. Then,use the VGG-16network for feature extraction,semantic attention mechanism is used to generate high-quality image features,and use the jump connection metho d to enhance the gradient correlation of remote distances,so as to provide multi-sc ale and multilevel feature information for subsequent image restoration.Finally,the recursive featu re map is fused and decoded to generate a repair image.The experimental results show that the proposed method,compared with traditional image inpainting methods,can improved the peak signal-to-noise ratio of the crack image repaired for 0.5dB—1.2dB and produce seman tic clear inpainting results.