Image super-resolution is a popular task that aims to translate images from low resolution to high resolution. For this task, convolutional networks are often used. Convolutional neural networks, have a great advantage in image processing. But despite this, often information can be lost during processing and increasing the depth and width of the network can make further work difficult. To solve this problem, data transformation into frequency domain is used. In this paper, the image is divided into high frequency and low frequency regions, where higher priority is given to the former. Then with the help of quality check, and visual evaluation, the method is analyzed and the conclusion regarding the performance of the algorithm is drawn.trial enterprise.

Keywords: super-resolution (SR), low-resolution (LR), high-resolution (HR), discrete-cosine transform, convolution-neural networks

This paper considers the problem of removing noise from an image based on the discrete cosine transform (DCT) algorithm. Despite its simplicity, the algorithm is still popular in image conversion. However, recently there has been a strong development of convolutional neural networks, leaving behind “traditional” signal processing methods. In this paper, we study image denoising using DCT and convolutional neural networks and creating an interpretable convolutional neural network to obtain accurate data. The basis was the Python programming language and the library for working with neural networks – PyTorch. Based on this, a neural network model was trained on The Berkeley Segmentation Dataset. Experiments have shown that the trained neural network shows results comparable to traditional image denoising algorithms.

Keywords: noise reduction, convolutional neural network, discrete cosine transform, machine learning, signal processing, Canny operator