Abstract:
The noise, poor image contrast, in homogeneity, weak boundaries and special mark existing in the mammogram images makes diagnosis procedure extremely difficult, so there are needs for a way to denoise the mammogram images while preserving the important features of the image.
The Adaptive bilateral filter sharpens an image by increasing the slope of the edges without producing overshoot or undershoot, its able to smooth the noise, while enhancing edges and textures in the image. Morphology operations such as dilation, erosion, opening and closing with appropriate structure element size are offering a quality Sharpening enhancement. The performance of the filter is to be improved by including the mathematical morphology operations along with adaptive bilateral filter process. The parameters of the Adaptive bilateral filter are optimized with a training procedure. Adaptive bilateral filter is removing noise from the images gives significantly sharper than those restored by the ordinary bilateral filter. The present proposed method is the modified algorithm of an adaptive bilateral filter with mathematical morphology operations for medical images. The proposed algorithm applied to various types of mammogram images after adding Gaussian noise and results are obtained. The performance analysis of the filter with respective design parameters and metrics are compared with existed algorithm the results were judged by three metrics; mean square error (MSE), structure similarity index (SSIM) and peak signal to noise ratio (PSNR). And relative graphs are depicted.
