• 대한방사선기술학회지:방사선기술과학
• /
• 제44권6호
• /
• pp.655-661
• /
• 2021

Positron emission tomography (PET) images is affected by acquisition time, short acquisition times results in low gamma counts leading to degradation of image quality by statistical noise. Noise2Void(N2V) is self supervised denoising model that is convolutional neural network (CNN) based deep learning. The purpose of this study is to evaluate denoising performance of N2V for PET image with a short acquisition time. The phantom was scanned as a list mode for 10 min using Biograph mCT40 of PET/CT (Siemens Healthcare, Erlangen, Germany). We compared PET images using NEMA image-quality phantom for standard acquisition time (10 min), short acquisition time (2min) and simulated PET image (S2 min). To evaluate performance of N2V, the peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE), structural similarity index (SSIM) and radio-activity recovery coefficient (RC) were used. The PSNR, NRMSE and SSIM for 2 min and S2 min PET images compared to 10min PET image were 30.983, 33.936, 9.954, 7.609 and 0.916, 0.934 respectively. The RC for spheres with S2 min PET image also met European Association of Nuclear Medicine Research Ltd. (EARL) FDG PET accreditation program. We confirmed generated S2 min PET image from N2V deep learning showed improvement results compared to 2 min PET image and The PET images on visual analysis were also comparable between 10 min and S2 min PET images. In conclusion, noisy PET image by means of short acquisition time using N2V denoising network model can be improved image quality without underestimation of radioactivity.

• 한국인공지능학회지
• /
• 제12권3호
• /
• pp.1-7
• /
• 2024

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.427-438
• /
• 2023

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.

• 대한의용생체공학회:의공학회지
• /
• 제28권6호
• /
• pp.756-767
• /
• 2007

For the combination of phosphor screens having various thicknesses and a photodiode array manufactured by complementary metal-oxide-semiconductor (CMOS) process, we report the observation of image-quality degradation under the irradiation of 45-kVp spectrum x rays. The image quality was assessed in terms of dark pixel signal, dynamic range, modulation-transfer function (MTF), noise-power spectrum (NPS), and detective quantum efficiency (DQE). For the accumulation of the absorbed dose, the radiation-induced increase both in dark signal and noise resulted in the gradual reduction in dynamic range. While the MTF was only slightly affected by the total ionizing dose, the noise power in the case of $Min-R^{TM}$ screen, which is the thinnest one among the considered screens in this study, became larger as the total dose was increased. This is caused by incomplete correction of the dark current fixed-pattern noise. In addition, the increase tendency in NPS was independent of the spatial frequency. For the cascaded model analysis, the additional noise source is from direct absorption of x-ray photons. The change in NPS with respect to the total dose degrades the DQE. However, with carefully updated and applied correction, we can overcome the detrimental effects of increased dark current on NPS and DQE. This study gives an initial motivation that the periodic monitoring of the image-quality degradation is an important issue for the long-term and healthy use of digital x-ray imaging detectors.

• 방송공학회논문지
• /
• 제27권5호
• /
• pp.808-811
• /
• 2022

강한 외부 조도 아래에서의 디스플레이는 인간의 인지 시스템에 의해, 실제보다 더 어둡게 인지된다. 해당 문제를 소프트웨어 측면에서 해결하기 위한 기존의 기법들은, 외부 조도에 대응하지 못하거나 밝기에 비해 색상이 향상되지 못하는 한계를 보인다. 따라서 본 논문은 외부 조도 값에 따라 영상의 밝기 및 색상을 향상하는 시인성 개선 알고리즘을 제안한다. 해당 알고리즘은 입력 영상과 함께 외부 조도 값을 인자로 받은 후, 딥러닝 모델을 통한 luminance 학습 및 chrominance 복원 방정식을 적용하여, 개선된 영상의 열화 현상과 입력 영상과의 대비 차이가 최소화되도록 영상을 생성한다. 이는 정성적 평가에서 열화 모델링 적용 영상 비교를 통해 해당 알고리즘이 강한 외부 조도 아래에서의 시인성 개선에 뛰어난 성능을 보임을 확인할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.55-61
• /
• 2019

Almost all 3D displays have a brightness reduction in the 3D mode comparing to the 2D mode. When the brightness is reduced, one of the color attributes, the colorfulness, is decreased. In this case, the viewer feels that the image quality is deteriorated. In this paper, we proposed a method to compensate for the degradation of colorfulness due to brightness reduction in 3D mode for high quality 3D image viewing using the CIECAM02 model and the color correction matrix. As a result of applying the proposed method, we can confirm that the colorfulness is improved in 3D mode.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 C
• /
• pp.1611-1613
• /
• 2000

In this study in order to find out the trends and the residual lifetime for electric connections/contacts using infrared image camera, "lifetime temperature rise model" is theoretically proposed on the base of "lifetime resistance model" and to prove this theory, experiments have been performed for various kinds of electric connections/contacts. Two suggestions have been builded up or the "lifetime temperature rise model" ; one is the linear relationship between the temperature rise $\Delta K$ and contact resistance, and the other is the functional relationship between the temperature of electric connections/contacts and the operating time which ascribed in the "lifetime resistance model". From the experimental results, measured values were quite similar to the theoretical value so that two suggestions in "lifetime temperature rise model" were appeared to be correct.

• 한국표면공학회지
• /
• 제54권5호
• /
• pp.278-284
• /
• 2021

Corrosion of steel plate is common phenomenon which results in the gradual destruction caused by a wide variety of environments. Corrosion monitoring is the tracking of the degradation progress for a long period of time. Corrosion on steel plate appears as a discoloration and any irregularities on the surface. In this study, we developed a quantitative evaluation method of the rust formed on steel plate by using k-means clustering from the corroded area in a given image. The k-means clustering for automated corrosion detection was based on the GrabCut segmentation and Gaussian mixture model(GMM). Image color of the corroded surface at cut-edge area was analyzed quantitatively based on HSV(Hue, Saturation, Value) color space.

• 한국음향학회지
• /
• 제8권4호
• /
• pp.39-43
• /
• 1989

본 논문에서는 crossed-array의 형태를 갖는 전승형 초음파 영상시스템의 모델링 방법을 소개한다. 12MHz에서 동작하는 crossed-array 시스템은 angular spectrum을 사용하여 simulation을 수행하였다. 또한 이론적인 연구를 통하여 시스템의 전달함수인 1M 매트릭스를 구하였다. 1M을 통하여 시스템의 degradation에 대한 model을 얻었으며, 그 특성이 이중구조를 갖는 Toeplitz 매트릭스가 됨을 알 수 있었다. 매트릭스 1M의 역을 구함으로써 초음파 영상의 spatial degradation을 제거시켰다.

• 한국컴퓨터정보학회논문지
• /
• 제27권9호
• /
• pp.21-32
• /
• 2022

이미지에 레이블을 부착하는 레이블링은 객체 탐지를 수행하기 위해서는 반드시 선행되어야 하며 이러한 작업은 딥러닝 모델을 구축하는 데 있어서 큰 부담으로 여겨지고 있다. 딥러닝 모델을 훈련하기 위해서는 수 만장의 이미지가 필요하며 이러한 이미지에 인간 레이블러가 직접 레이블링을 진행하기에는 많은 한계가 있다. 이러한 어려움을 극복하기 위해 본 연구에서는 전체 이미지가 아닌 일부 이미지에 대한 레이블링을 통해서도 큰 성능의 저하 없이 객체 탐지를 수행하는 방안을 제안한다. 구체적으로 본 연구에서는 저품질 동양화 이미지의 객체 탐지를 위해 초고해상화 알고리즘을 이용하여 저해상도의 이미지를 고화질의 이미지로 변환하고, 이 과정에서 도출되는 SSIM과 PSNR이 객체 탐지의 mAP에 미치는 영향을 분석하여 객체 탐지 분석에 필요한 레이블링을 위한 최적의 샘플링을 수행하는 방안을 제안한다. 본 연구의 결과는 이미지 레이블링을 필요로 하는 이미지 분류, 객체 검출, 이미지 분할 등 딥러닝 모델 구축에 크게 기여할 수 있을 것으로 기대한다.