Decision level based Image Fusion using Wavelet Transform and Support Vector Machine

Image Fusion is a process of combining the relevant information from a set of images, into a single image, wherein the resultant fused image will be more informative and complete than any of the input images. The fusion methods for combining infrared images with visible spectrum images concentrate heavily on the surveillance and remote sensing applications Decision level based image fusion using Shift Invariant Discrete Wavelet transform and SVM is presented here. Shift invariance of the wavelet transform is important in ensuring robust sub-band fusion. Support Vector Machine is trained to select the coefficient blocks with significant features, extracted from the SIDWT coefficients. The performance of the proposed scheme is evaluated by various quantitative measures like Mutual Information (MI), Standard deviation, and Entropy (EN). Visual and quantitative analysis show the effectiveness of the proposed scheme in fusing multimodality images.