• Title/Summary/Keyword: U-Net, Patch-GAN

Search Result 3, Processing Time 0.019 seconds

An Efficient CT Image Denoising using WT-GAN Model

  • Hae Chan Jeong;Dong Hoon Lim
    • 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.

Improving Confidence in Synthetic Infrared Image Refinement using Grad-CAM-based Explainable AI Techniques (Grad-CAM 기반의 설명가능한 인공지능을 사용한 합성 이미지 개선 방법)

  • Taeho Kim;Kangsan Kim;Hyochoong Bang
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.27 no.6
    • /
    • pp.665-676
    • /
    • 2024
  • Infrared imaging is a powerful non-destructive and non-invasive technique to detect infrared radiations and capture valuable insights inaccessible through the visible spectrum. It has been widely used in the military for reconnaissance, hazard detection, night vision, guidance systems, and countermeasures. There is a huge potential for machine learning models to improve trivial infrared imaging tasks in military applications. One major roadblock is the scarcity and control over infrared imaging datasets related to military applications. One possible solution is to use synthetic infrared images to train machine learning networks. However, synthetic IR images present a domain gap and produce weak learning models that do not generalize well. We investigate adversarial networks and Explainable AI(XAI) techniques to refine synthetic infrared imaging data, enhance their realism, and synthesize refiner networks with XAI. We use a U-Net-based refiner network to refine synthetic infrared data and a PatchGAN discriminator to distinguish between the refined and real IR images. Grad-CAM XAI technique is used for network synthesis. We also analyzed the frequency domain patterns and power spectra of real and synthetic infrared images to find key attributes to distinguish real from synthetic. We tested our refined images on the realism benchmarks using frequency domain analysis.

ISFRNet: A Deep Three-stage Identity and Structure Feature Refinement Network for Facial Image Inpainting

  • Yan Wang;Jitae Shin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.17 no.3
    • /
    • pp.881-895
    • /
    • 2023
  • Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.