• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.145-147
• /
• 2022

본 논문에서는 훼손되어 식별할 수 없는 탑 이미지를 비롯해 낮은 해상도의 탑 이미지를 개선하기 위해 우리는 탑 이미지의 화질 개선을 인공지능을 이용하여 빠르게 개선을 해 보고자 한다. 최근에 Generative Adversarial Networks(GANS) 알고리즘에서 SrGAN 알고리즘이 나오면서 이미지 생성, 이미지 복원, 해상도 변화 분야가 지속해서 발전하고 있다. 이에 본 연구에서는 다양한 GAN 알고리즘을 화질 개선에 적용해 보았다. 탑 이미지에 GAN 알고리즘 중 SrGan을 적용하였으며 실험한 결과 Srgan 알고리즘은 학습이 진행되었으며, 낮은 해상도의 탑 이미지가 높은 해상도, 초고해상도 이미지가 생성되는 것을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.479-481
• /
• 2023

Generative Adversarial Networks (GANs) have facilitated substantial improvement in single-image super-resolution (SR) by enabling the generation of photo-realistic images. However, the high memory requirements of GAN-based SRs (mainly generators) lead to reduced performance and increased energy consumption, making it difficult to implement them onto resource-constricted devices. In this study, we propose an efficient and compressed architecture for the SR-GAN (generator) model using the model compression technique Knowledge Distillation. Our approach involves the transmission of knowledge from a heavy network to a lightweight one, which reduces the storage requirement of the model by 58% with also an increase in their performance. Experimental results on various benchmarks indicate that our proposed compressed model enhances performance with an increase in PSNR, SSIM, and image quality respectively for x4 super-resolution tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.1
• /
• pp.99-109
• /
• 2022

This study is the first report on production and characterization of the enzyme from an Ornithinibacillus species. A 4.2-fold increase in the extracellular protease (called L9^T) production from Ornithinibacillus caprae L9^T was achieved through the one-factor-at-a-time approach and response surface methodological optimization. L9^T protease exhibited a unique protein band with a mass of 25.9 kDa upon sodium dodecyl sulfate-polyacrylamide gel electrophoresis. This novel protease was active over a range of pH (4-13), temperatures (30-80℃) and salt concentrations (0-220 g/l), with the maximal activity observed at pH 7, 70℃ and 20 g/l NaCl. Proteolytic activity was upgraded in the presence of Ag⁺, Ca²⁺ and Sr²⁺, but was totally suppressed by 5 mM phenylmethylsulfonyl fluoride, which suggests that this enzyme belongs to the serine protease family. L9^T protease was resistant to certain common organic solvents and surfactants; particularly, 5 mM Tween 20 and Tween 80 improved the activity by 63 and 15%, respectively. More importantly, L9^T protease was found to be effective in dehairing of goatskins, cowhides and rabbit-skins without damaging the collagen fibers. These properties confirm the feasibility of L9^T protease in industrial applications, especially in leather processing.