Adaptive Neuro-Fuzzy Inference System for Noise Expulsion
A. Rajamani, Krishnaveni V V · International journal of tomography and simulation · 2015
Visual communication plays vital role in modern trend and finds its applications in many image processing domains. While transmitting and storing the digital information, images are affected by different types of noises. Moreover images are often corrupted by source of noise due to a noisy channel or faulty image acquisition device. Many researchers have developed several algorithms for removing noise. The main aim is to suppress the noise while preserving the integrity of the edges and details of images. This paper exploits the soft computing technique of Adaptive Network based Fuzzy Inference System which is also known as Adaptive Neuro-Fuzzy Inference System (ANFIS) for different level of noise removal. It is presently finding numerous applications in variety of fields since Neuro-Fuzzy system adaptive of the Fuzzy system and the neural learning algorithm. The parameters are learned by Neural Network using optimized learning method. This paper deals with restoration of images from different noise sources by using ANFIS with different Membership Functions [MFs] and training epochs are examined. The technique outperforms and the results obtained are very good in both qualitative and quantitative wise.