On the Adaptability of Neural Network Image Super-Resolution

TL;DR

This paper presents a framework using Multilayer Perceptrons for image super-resolution, analyzing their performance across different image categories with various metrics, showing promising results for category-specific training.

Contribution

Introduces a neural network-based framework for image super-resolution and evaluates its performance across multiple image categories using standard quality metrics.

Findings

MLP trained on a single image category performs reasonably well.

The framework can be applied to low-level image processing tasks.

Performance varies with training data diversity.

Abstract

In this paper, we described and developed a framework for Multilayer Perceptron (MLP) to work on low level image processing, where MLP will be used to perform image super-resolution. Meanwhile, MLP are trained with different types of images from various categories, hence analyse the behaviour and performance of the neural network. The tests are carried out using qualitative test, in which Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The results showed that MLP trained with single image category can perform reasonably well compared to methods proposed by other researchers.