Image Enhancement Based on Contextual Thresholding Segmentation on Various Noise Deduction in Mammogram Images

Abstract: Due to deficient performance of X-ray on mammographic images are generally noisy with poor radiographic resolution. This leads to improper visualization of lesion details. The Image enhancement techniques are important for visual inspection. In this paper the combined features of enhancement technique and contextual thresholding method for segmentation with Adaptive volterra filters are usedto minimizing the effect of noises in the mammogram images. After the process of de-noising, the enhanced results will be segmented. Then we calculate the extracted tumor portions and it has been compared by the various quality metrics as Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Mean Absolute Error (MAE) and Root Relative Squared Error (RRSE) etc...This enhanced de-noising technique is used to tested more images and the performance evaluated based on their MSE and PSNR.The proposed enhanced denoising technique gives better result than existing de-noising technique. Keywords: Mammogram Images, De-noising, enhancement technique, Adaptive Volterra filter (AVF).