Image Noise Level Estimation for Rice Noise Based on Extended ELM Neural Network Training Algorithm

Abstract

The estimation of image noise level is a critical task for image denoising or super-resolution reconstruction. Mathematical methods like patch-based or model-based methods, suffer from the sensitivity of the selection of homogeneous regions or the selection of a proper statistic model, leading to inaccurate estimation, especially in signal-dependent noise cases, such as Rice noise. Ordinary, fully connected networks often suffer from the over-fitting problem, restricting their usage for realistic images. This article proposes a deep-learning-based algorithm by building a deep neural network, and train it by using the evolutionary genetic algorithm and extreme learning machine (ELM) algorithm extended into Hinton's dropout framework. By combining the evolutionary genetic algorithm and the proposed extended ELM algorithm, comparative results are obtained, showing higher accuracy and better stability than several stateof-the-art algorithms.INDEX TERMS Noise level estimation, deep learning, convolution neural network, extreme learning machine, dropout.

Application of ELM algorithm-based generative adversarial network model in network security

“…Finally, there is the network output layer, and the output layer is used to output the results. When a suitable network structure is chosen, this neural network can fit any continuous function without error [25][26][27]. The input network layer has 𝑗 network neuron, which represents each of the different input variables; the hidden network layer consists of 𝑘 network neurons; and the output network layer has 𝑖 neurons, which represent each of the different output variables.…”