Multi Focus and Multi-Source Image Fusion Based on Deep Learning Model

In order to realize the image fusion of multi focus and multi-source acquisition, in this paper a method based on deep learning model and DT-CWT image fusion is proposed. Firstly, the base parts and detail features of the image were separated, the base parts was denoised and filtered by DT-CWT, and the fusion base parts were obtained; depth learning model VGG-S was selected to extract the detail features of the image, and then the fusion details were obtained by multi-layer fusion strategy. Finally, the maximum gradient value is used to select the detail features to obtain the fusion details. The fusion base parts and details features were overlapped and reconstructed to obtain the fusion image. The algorithm not only retains the significant features of the image, but also makes the fused image obtain more detailed feature information. In the process, the noise was reduced. The subjective and objective evaluation results are improved obviously.