• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.21-29
• /
• 2024

Reducing the radiation dose during CT scanning can lower the risk of radiation exposure, but not only does the image resolution significantly deteriorate, but the effectiveness of diagnosis is reduced due to the generation of noise. Therefore, noise removal from CT images is a very important and essential processing process in the image restoration. Until now, there are limitations in removing only the noise by separating the noise and the original signal in the image area. In this paper, we aim to effectively remove noise from CT images using the wavelet transform-based GAN model, that is, the WT-GAN model in the frequency domain. The GAN model used here generates images with noise removed through a U-Net structured generator and a PatchGAN structured discriminator. To evaluate the performance of the WT-GAN model proposed in this paper, experiments were conducted on CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. As a result of the performance experiment, the WT-GAN model is better than the traditional filter, that is, the BM3D filter, as well as the existing deep learning models, such as DnCNN, CDAE model, and U-Net GAN model, in qualitative and quantitative measures, that is, PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) showed excellent results.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• Korean Journal of Materials Research
• /
• v.15 no.2
• /
• pp.106-111
• /
• 2005

Effects of stainless steel-making dusts and binder content on compacting $density(\rho)$ and magnetic properties were evaluated. Cores compacted with the mixture of pure Fe powders, $5wt.\%$ dusts and $0.25wt.\%$ binder showed good AC magnetic properties. For example, permeability$({\mu}a)$ and core loss(P) of the cores containing $5wt.\%$ dusts at 500 kHz were 62 and $4008\;{\mu}W/cm^3$, respectively. These properties are almost equivalent to those of competitor's products (i.e, Ancorsteel TC 80 produced by $H\ddot{o}gan\ddot{a}s$ Corp.). The powdered cores obtained from the present work are expected to apply for high-performance soft magnetic components such as normal mode choke filter and pulse transformer.

• Nuclear Engineering and Technology
• /
• v.46 no.2
• /
• pp.147-158
• /
• 2014

In order to investigate how the microstructure of fuel/matrix-interaction (FMI) layers change during irradiation, different U-7Mo dispersion fuel plates have been irradiated to high fission density and then characterized using scanning electron microscopy (SEM). Specifially, samples from irradiated U-7Mo dispersion fuel elements with pure Al, Al-2Si and AA4043 (~4.5 wt.%Si) matrices were SEM characterized using polished samples and samples that were prepared with a focused ion beam (FIB). Features not observable for the polished samples could be captured in SEM images taken of the FIB samples. For the Al matrix sample, a relatively large FMI layer develops, with enrichment of Xe at the FMI layer/Al matrix interface and evidence of debonding. Overall, a significant penetration of Si from the FMI layer into the U-7Mo fuel was observed for samples with Si in the Al matrix, which resulted in a change of the size (larger) and shape (round) of the fission gas bubbles. Additionally, solid fission product phases were observed to nucleate and grow within these bubbles. These changes in the localized regions of the microstructure of the U-7Mo may contribute to changes observed in the macroscopic swelling of fuel plates with Al-Si matrices.