Multi-resolution Image Fusion Algorithm Based on Gradient and Texture Features

A multi-resolution image fusion algorithm based on gradient and texture features is proposed. After each level of Gaussian Pyramid being separately filtered by texture-extracting filters and edge gradient filters, a series of texture and edge images including the texture information of original image are generated. This provides more comprehensive information measurement for further fusion. Infrared and visible images are fused utilizing the proposed image fusion method, and the fusion results are compared with several traditional fusion method. Experiment results and image fusion quality assessment show that the proposed fusion method demonstrates more superiority.