Reconstruction algorithms with images inferred by self-organizing maps

For restoring a degraded image, reconstruction algorithms with images inferred by self-organizing maps are presented in this study. Multiple images inferred by self-organizing maps are prepared in the initial stage, which creates a map containing one unit for each pixel. Utilizing pixel values as input, image inference is conducted by self-organizing maps. An updating function with threshold according to the difference between input value and inferred value is introduced, so as not to respond to noisy input sensitively. The inference of an original image proceeds appropriately since any pixel is influenced by neighboring pixels corresponding to the neighboring setting. By using the inferred images, two approaches are presented. The first approach is that a pixel value of a restored image is a median value of inferred images for respective pixels. The second approach is that a pixel value is an average value of them. Experimental results are presented in order to show that our approach is effective in quality for image restoration.