Elimination of Gaussian Noise using Post Processing

Elimination of Gaussian Noise using Post Processing

1Dr.R.Pushpavalli, 2K.Dharshini, 3V.Dharshini

1Associate Professor, 2, 3Student

Department of Electronics and Communication Engineering

Paavai Engineering College, Namakkal, India, 637018

pushpasivaramanpec@paavai.edu.in, dharshini30032002@gmail.com, kaviyavarutharaj@gmail.com

Abstract—Image denoising is a noise elimination technique in digital image processing during transmission over the communication channel. Due to uneven illumination, image blurring, low contrast, image with poor quality is not useful for further application. Digital images are often degraded by Gaussian noise in order to obtain a better visual quality and mass communication signal-to-noise ratio than other several state-of-the-algorithms. The non-linear noise on digital images detected and reduced by RAISR algorithms and the internal parameter of the feed forward neural network are adaptively optimized by training for well-known images. The results are compared with other existing filters like sobel filter for performance evaluation. The proposed technique is shown better performance than other existing techniques in terms of edge and fine details preservation. The primary image is obtained to get extremely well executed image. The results are specified by white pixels because they are independent of variables.

Keywords—RAISR, FFNN, Gaussian noise, Pixels, Sobel filter