Open AccessKNN Classification Based Nonlinear Noise Delineation in Color Image using Optimized BM3D Filter
Author(s) -
Mr. Mandar D. Sontakke,
Meghana Kulkarni
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.i7610.0881019
Subject(s) - artificial intelligence , pixel , computer science , noise (video) , computer vision , filter (signal processing) , pattern recognition (psychology) , process (computing) , image (mathematics) , operating system
Image enhancement using optimized methods along with optimized filters is need of current era. A novel technique is proposed in this paper, which have KNN based pixels classifications strategy. This classification is used to identify noise level and only noisy pixels are processed using optimized BM3D using particle swarm optimization. The outside group pixels are brought back into group thereby removing the noise. The process is further followed by resolution enhancement and Retinex for dynamic presentation purpose. The experimentation results are also included in the paper which shows optimum performance.