Title :
Neural Network Adaptive Switching Median Filter for Image Denoising
Author :
Apalkov, Ilya V. ; Zvonarev, Pavel S. ; Khryashchev, Vladimir V.
Author_Institution :
Digital Circuits & Signals Lab., P.G. Demidov Yaroslavl State Univ.
Abstract :
A new neural network adaptive switching median (NASM) filter is proposed to remove salt-and-pepper impulse noise from highly corrupted image. The algorithm is developed by combining advantages of the known progressive median filter with impulse detection scheme. Neural network was included into impulse detection step to improve its characteristics. Comparison of the given method with traditional median-type filters is provided
Keywords :
adaptive filters; image denoising; impulse noise; median filters; neural nets; adaptive switching median filter; highly corrupted image; image denoising; impulse detection; neural network; nonlinear image processing; progressive median filter; salt-and-pepper impulse noise removal; Adaptive filters; Adaptive systems; Image denoising; Image edge detection; Image processing; Information filtering; Information filters; Neural networks; Noise generators; Pixel; impulse noise removal; neural network; nonlinear image processing; switching median filter;
Conference_Titel :
Computer as a Tool, 2005. EUROCON 2005.The International Conference on
Conference_Location :
Belgrade
Print_ISBN :
1-4244-0049-X
DOI :
10.1109/EURCON.2005.1630106
