A Contrast Adjusted Wavelet and Curvelet Transform Based Fusion of Breast Images

Abstract

Abstract Restoration is one of the image processing techniques to restore the distorted image. The distorted image can be any type like blurred image, noise added either while storing or capturing of the images. the traditional restoration techniques are geometric correction, different types of filters to remove the noises. Generally, the restoration is applied to the single image to retrives its information. In this, the restoration process is applied in the application of image fusion of medical images. the reason to chose the image fusion process is to improve its entropy. The medical images used in this paper is the mammogram and MRI-breast image. In this, the image fusion is performed with the help of wavelet and curvelet transform. The curvelet transform is applied to the restored mammogram image with the help of contrast adjusted top-hat filter process. The wavelet transform is applied to the MRI image because it has more volume of data to acquire important details. The fused image is evaluated with the help of entropy, mean standard deviation and variance. The fused image has efficient value as compared to its original image but it is higher than the DTCWT-fused image. To verify the quality of the proposed method, the psnr is evaluated to determine the noise present in the image. From the evaluation, the noise is less and entropy is higher in the proposed method. Hence, the contrast adjusted wavelet curvelet fusion is the best restoration and fusion process in the breast images.