ANN based Adaptive Thresholding for Impulse Detection

B. Majhi, P.K. Sa, and G.K. Panda (India)


Random valued impulsive noise, artificial neural network, median filter, multi layer perceptron, impulse detection, adaptive threshold.


In this paper a novel filtering scheme has been proposed for the removal of random valued impulsive noise from im ages. The scheme is based on a second order differential impulse detection mechanism followed by a recursive me dian filter. The salient feature of the impulse detector is that it utilizes an adaptive threshold derived from an ar tificial neural network. The neural network predicts the threshold using inputs from the noisy image characteristics and achieves generalization. It is observed from exhaustive computer simulation results that the proposed scheme out performs the existing reported strategies in terms of noise rejection and detail preservation. In addition, as the pro posed scheme uses a selective filter, the computation over head is less in comparison to others.

Important Links:

Go Back