Color image processing in a cellular neural-network environment

Abstract

Abstract-When low-level hardware simulations of cellular neural networks (CNN's) are very costly for exploring new applications, the use of a behavioral simulator becomes indispensable. This paper presents a software prototype capable of performing image processing applications using CNN's. The software is based on a CNN multilayer structure in which each primary color is assigned to a unique layer. This allows an added flexibility as different processing applications can be performed in parallel. To be able to handle a full range of color tones, two novel color mapping schemes were derived. In the proposed schemes the color information is obtained from the cell's state rather than from its output. This modification is necessary because for many templates CNN has only binary stable outputs from which only either a fully saturated or a black color can be obtained. Additionally, a postprocessor capable of performing pixelwise logical operations among color layers was developed to enhance the results obtained from CNN. Examples in the areas of medical image processing, image restoration, and weather forecasting are provided to demonstrate the robustness of the software and the vast potential of CNN..

Evaluation of the Traffic Parameters in a Metropolitan Area by Fusing Visual Perceptions and CNN Processing of Webcam Images

“…From these formulas, it is easy to understand that solving a particular image processing problem implies as a first step the identification of the appropriate values of the coefficients of the matrices , and , also known as CNN templates, as outlined in [43] and [44]. The values of the CNN templates can be found according to a learning algorithm as the one that allows us to obtain the known final image from the initial image for any pair of a possibly wide learning set of image pairs in which the two images of any pair are linked by the same relation , e.g., images are the noiseless images whereas images are the corresponding images affected by white noise.…”

DMF-Net: a deep multi-level semantic fusion network for high-resolution chest CT and X-ray image de-noising

“…Also by raising the depth or modifying the activation function, novel network designs shown competitive in removing noise [ 10 ]. But these models require parameters to be set manually and it got resolved with gradient descent [ 11 , 12 ]. Because of the aforementioned reasons, convolutional neural networks (CNNs) were proposed with vanishing gradients and different activation functions such as sigmoid [ 13 ] and tanh [ 14 ] but it needs a computationally effective platform to implement.…”