An Efficient Image Fusion of Visible and Infrared Band Images using Integration of Anisotropic Diffusion and Discrete Wavelet Transform

Binal Panchotiya, Dippal Israni, Ritesh Patel


Image fusion is a technique that combines two source images to generate more informative target image. It plays a vital role in medical image investigation, military, navigation, etc. visible images offer efficient texture detail with high spatial resolution. In contrast, based on the radiation difference infrared images are able to differentiate target from their background. There are many algorithms that helps in preserving the edges of image like Bilateral filter, anisotropic diffusion (ADF). This paper integrates Anisotropic Diffusion and Karhunen-Loeve (KL)Transformation with discrete wavelet transform (DWT). In proposed Method, DWT decomposes into four sub-bands. ADF is applied on approximation sub-band and absolute maximum selection is applied on other three sub-bands. ADF decomposes the image into detailed layer and base layer. Base layer and Detailed layer are calculated using Kl- Transformation and linear combination respectively. Once fusion is done, inverse DWT is applied on all sub-bands. The experimental outcomes depict that the offered approach result with sharp edges of the image. The proposed algorithm is evaluated on standard dataset Like Duine_Sequence, Tree_sequence, Street dataset. Standard metrics like Average Gradients and Spatial Frequency metrics are used to evaluate the performance of the image.


Image fusion; Infrared and Visible image; DWT; Anisotropic Diffusion

Full Text:



Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.