ENHANCEMENT OFMAMMOGRAM IMAGES EFFECTIVELY USING DOUBLE FILTERING TECHNIQUE

Abstract

Breast cancer is the most common death causing cancer among women. Mammograms are used as a
best screening tool to detect early breast cancer and processing of these images requires high computational
capabilities.Due to ill-performance of X-ray hardware systems, mammographic images are generally noisy with
poor radiographic resolution. This leads to improper visualization of lesion detail. Mammogram enhancementis an
important preprocessing technique for identifying mass and micro-calcification. Non-linear filters are generally
preferred for image enhancement applications as they provide better filtering results not only by suppressing
background noise but also preserving the edges. In this paper, a mammogram image which is affected by salt and
pepper noise is considered.The proposed method presents a combination of Adaptive Volterra filter withany one
of existing filters like mean,median, min-max may be used for contrast enhancement of mammograms. For
comparison, mammogram which is corrupted by Gaussian, Poisson and white noise is considered.These noises are
eliminated using four combination of filters and the performance of filters is evaluated by calculating peak signal
to noise ratio (PSNR) and Mean square error(MSE).