Performance of Feature level fusion of Multi-focused images using Stationary Wavelet Packet Transform

Image fusion is defi ned as the process of combining two or more different images into a new single image retaining important features from each image with extended information content. There are two approaches to image fusion, namely spatial fusion and transform fusion and three levels namely pixel, feature and region level. In spatial fusion, the pixel values from the source images are directly summed up and taken average to form the pixel of the composite image at that location. Transform fusion uses transform for representing the source image at multi scale. The most common widely used transform for image fusion at multi scale is Discrete Wavelet Transform since it minimizes structural distortions. But, Discrete Wavelet Transform suffers from lack of shift invariance and poor directionality. One way to avoid these disadvantages is dual tree complex wavelet transform which is expensive, computationally intensive and approximately shift invariant. But, the un-decimated discrete wavelet transform, namely Stationary Wavelet Transform is shift invariant and Wavelet Packet transform provides more directionality. In this paper, it is proposed to combine Stationary Wavelet Transform & Wavelet Packet Transform to form Stationary Wavelet Packet Transform which is applied to feature level fusion of multi-focused images and performance is measured in terms of Peak Signal to Noise Ratio, Root Mean Square Error, Quality Index and Normalized Weighted Performance Metric.