Multi-Channel FLANN Adaptive Filter for Speckle & Impulse Noise Elimination from Color Doppler Ultrasound Images

Abstract

The conventional fixed filters cannot be employed for removing the mixed noise of Color Doppler Ultrasound (CDUS) images because it affects the features of the image awkwardly. Consequently, identifying an internal blockage or hemorrhage of the patient become arduous in such conditions. Hence, the evolutionary multi-channel Functional Link Artificial Neural Network (M-FLANN) has been proposed to get rid of Speckle noise from the CDUS images. In this paper, the performance of the M-FLANN and other five competitive filters is evaluated in terms of qualitative and quantitative measures.