In this paper we have proposed a computationally efficient artificial neural network (ANN) for the purpose of adaptive image filtering. The major drawback of feed forward networks such as multilayer perceptron (MLP) trained with Back Propagation (BP) algorithm is that it requires a large amount of computation time for learning. We propose a single layer functional link ANN (FLANN) in which the need of hidden layer is eliminated by expanding the input pattern by different functional expansions. The novelty of this network is that it requires less computation than that of MLP. We have shown the effectiveness in the problem of filtering an image corrupted with different noises such as additive white Gaussian noise, impulse noise or both of these two, salt & pepper noise, multiplicative noises, random value impulse noise etc. at the time of transmission. To avoid this noise, FLANN based adaptive image filters are used. This can be better utilized in online application. The result is also compared to that of MLP classifier. It is observed that the proposed network is computationally cheap and gives better classification accuracy than that of MLP

Salt &pepper Noise Gaussian Noise Impulse Noise Multiplicative Noise Mlp Flann