Image Super-Resolution using Generative Adversarial Networks with EfficientNetV2

• Published in: International journal of advanced computer science & applications Vol. 14; no. 2
• Main Authors: AlTakrouri, Saleh, Noor, Norliza Mohd, Ahmad, Norulhusna, Justinia, Taghreed, Usman, Sahnius
• Format: Journal Article
• Language: English
• Published: West Yorkshire Science and Information (SAI) Organization Limited 2023
• Subjects: Discriminators; Domains; Generative adversarial networks; Image processing; Image quality; Image reconstruction; Image resolution; Mean square errors; Medical imaging; Remote sensing; Signal to noise ratio; Target recognition
• ISSN: 2158-107X; 2156-5570
• DOI: 10.14569/IJACSA.2023.01402100

The image super-resolution is utilized for the image transformation from low resolution to higher resolution to obtain more detailed information to identify the targets. The super-resolution has potential applications in various domains, such as medical image processing, crime investigation, remote sensing, and other image-processing application domains. The goal of the super-resolution is to obtain the image with minimal mean square error with improved perceptual quality. Therefore, this study introduces the perceptual loss minimization technique through efficient learning criteria. The proposed image reconstruction technique uses the image super-resolution generative adversarial network (ISRGAN), in which the learning of the discriminator in the ISRGAN is performed using the EfficientNet-v2 to obtain a better image quality. The proposed ISRGAN with the EfficientNet-v2 achieved a minimal loss of 0.02, 0.1, and 0.015 at the generator, discriminator, and self-supervised learning, respectively, with a batch size of 32. The minimal mean square error and mean absolute error are 0.001025 and 0.00225, and the maximal peak signal-to-noise ratio and structural similarity index measure obtained are 45.56985 and 0.9997, respectively.