A New Image Enhancement Technique using Local-Correlation based Fusion using Wavelet Transform

Abstract

Fusion of images is the process of extracting important features from two or more images of the same scene into a single image for the better visual perception and computer processing tasks such as segmentation, feature extraction and object recognition. Discrete wavelet transform (DWT) allows the image decomposition for preserving the discrete image information. DWT is applied to analyze the images efficiently in detail. This paper proposed a new image enhancement scheme using wavelet transform based on local-correlation based fusion strategy. The proposed method is compared with the standard DWT and Stationary Wavelet Transform (SWT) method of fusion using max and avg rule. The experimental results are evaluated and compared using visual appearance and quantitative measure like Peak Signal to Noise Ratio and Correlation Coefficient. The proposed work is best in removing the blurred regions and maintains the smoothness in the homogeneous part of the image.