• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.567-569
• /
• 2023

GAN은 이미지 생성모델로서 이미지 공간에서 좋은 결과를 보여왔다. 우리는 이러한 GAN의 능력을 더욱 향상하기 위하여 본 연구에서 주파수 영역에서 이미지를 학습하고 생성하는 새로운 방법을 제안한다. 이를 위하여 먼저 학습데이터를 2D FFT로 주파수 영역으로 변환한 후 변환된 학습데이터를 GAN이 학습하게 한다. 학습 후에 GAN은 새로운 이미지를 생성하며 생성된 이미지를 2D IFFT하여 이미지 공간으로 변환한다. 이렇게 주파수 영역에서 이미지를 생성하는 방법은 이미지 공간에서 생성하는 방법보다 다양한 장점이 있다. 생성된 이미지의 품질을 평가하기 위하여 4개 데이터 셋에 4개의 평가지표를 사용하여 평가한 결과 주파수 영역에서 생성한 이미지가 IS, P&R, D&C 측면에서 더 좋은 것으로 평가되었다.

• 문화기술의 융합
• /
• 제8권6호
• /
• pp.867-871
• /
• 2022

최근 빠른 유행의 변화 속에서 디자인의 변화는 패션기업의 매출에 큰 영향을 미치기 때문에 기업들은 신제품디자인 선택에 신중할 수밖에 없다. 최근 인공지능 분야의 발달에 따라 패션시장에서도 소비자들의 선호도를 높이기 위해 다양한 기계학습을 많이 활용하고 있다. 우리는 선호도와 같은 추상적인 개념을 수치화함으로써 신제품 개발에 신뢰성을 높이는 부분에 기여하고자 한다. 이를 위해 3가지 적대적 생성 신경망(Generative adversial netwrok, GAN)을 통하여 기존에 없는 새로운 이미지를 생성하고, 미리 훈련된 합성곱 신경망(Convolution neural networkm, CNN)을 이용하여 선호도라는 추상적인 개념을 수치화시켜 비교하였다. 심층 컨볼루션 적대적 생성 신경망(Deep convolutional generative adversial netwrok, DCGAN), 점진적 성장 적대적 생성 신경망(Progressive growing generative adversial netwrok, PGGAN), 이중 판별기 적대적 생성 신경망(Dual Discriminator generative adversial netwrok, D2GAN)의 3가지 방법을 통해 새로운 이미지를 생성하였고, 판매량이 높았던 제품으로 훈련된 합성곱 신경망으로 유사도를 비교, 측정하였다. 측정된 유사도의 정도를 선호도로 간주하였으며 실험 결과 D2GAN이 DCGAN, PGGAN에 비해 상대적으로 높은 유사도를 보여주었다.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1391-1402
• /
• 2021

This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.

• 한국약용작물학회지
• /
• 제25권3호
• /
• pp.165-174
• /
• 2017

Background: Traditional plant drugs, are less toxic and free from side effects compared to general synthetic drugs. They have been used for the treatment of diabetes and associated renal damage. In this study, we evaluated effect of Hachimi-jio-gan against diabetic renal damage in a rat model of type 1 diabetic nephropathy induced by subtotal nephrectomy plus streptozotocin (STZ) injection, and in Otsuka Long-Evans Tokushima Fatty (OLETF) rats and db/db mice as a model of human type 2 diabetes, and its associated complications. To explore the active components of Hachimi-jio-gan, the antidiabetic effect of corni fructus, a consituent of Hachimi-jio-gan, and 7-O-galloyl-${{\small}D}$-sedoheptulose, a phenolic compound isolated from corni fructus, were investigated. Methods and Results: We conducted an extensive literature search, and all required data were collected and systematically organized. The findings were reviewed and categorized based on relevance to the topic. A summary of all the therapeutic effects were reported as figures and tables. Conclusions: Hachimi-jio-gan serves as a potential therapeutic agent to against the development of type 1 and type 2 diabetic nephropathy. From the results of characterization active components of corni fructus, 7-O-galloyl-${\small}D$-sedoheptulose is considered to play an important role in preventing and/or delaying the onset of diabetic renal damage. 7-O-Galloyl-${\small}D$-sedoheptulose is expected to serve as a novel therapeutic agent against the development of diabetic nephropathy.

• 한국IT서비스학회지
• /
• 제22권5호
• /
• pp.87-98
• /
• 2023

Traditionally, tooth restoration has been carried out by replicating teeth using plaster-based materials. However, recent technological advances have simplified the production process through the introduction of computer-aided design(CAD) systems. Nevertheless, dental restoration varies among individuals, and the skill level of dental technicians significantly influences the accuracy of the manufacturing process. To address this challenge, this paper proposes an approach to designing personalized tooth restorations using Generative Adversarial Network(GAN), a widely adopted technique in computer vision. The primary objective of this model is to create customized dental prosthesis for each patient by utilizing 3D data of the specific teeth to be treated and their corresponding opposite tooth. To achieve this, the 3D dental data is converted into a depth map format and used as input data for the GAN model. The proposed model leverages the network architecture of Pixel2Style2Pixel, which has demonstrated superior performance compared to existing models for image conversion and dental prosthesis generation. Furthermore, this approach holds promising potential for future advancements in dental and implant production.

• 한국해양공학회지
• /
• 제36권1호
• /
• pp.32-40
• /
• 2022

Underwater optical images face various limitations that degrade the image quality compared with optical images taken in our atmosphere. Attenuation according to the wavelength of light and reflection by very small floating objects cause low contrast, blurry clarity, and color degradation in underwater images. We constructed an image data of the Korean sea and enhanced it by learning the characteristics of underwater images using the deep learning techniques of CycleGAN (cycle-consistent adversarial network), UGAN (underwater GAN), FUnIE-GAN (fast underwater image enhancement GAN). In addition, the underwater optical image was enhanced using the image processing technique of Image Fusion. For a quantitative performance comparison, UIQM (underwater image quality measure), which evaluates the performance of the enhancement in terms of colorfulness, sharpness, and contrast, and UCIQE (underwater color image quality evaluation), which evaluates the performance in terms of chroma, luminance, and saturation were calculated. For 100 underwater images taken in Korean seas, the average UIQMs of CycleGAN, UGAN, and FUnIE-GAN were 3.91, 3.42, and 2.66, respectively, and the average UCIQEs were measured to be 29.9, 26.77, and 22.88, respectively. The average UIQM and UCIQE of Image Fusion were 3.63 and 23.59, respectively. CycleGAN and UGAN qualitatively and quantitatively improved the image quality in various underwater environments, and FUnIE-GAN had performance differences depending on the underwater environment. Image Fusion showed good performance in terms of color correction and sharpness enhancement. It is expected that this method can be used for monitoring underwater works and the autonomous operation of unmanned vehicles by improving the visibility of underwater situations more accurately.

• 방송공학회논문지
• /
• 제28권1호
• /
• pp.109-123
• /
• 2023

딥러닝은 최근 몇 년 동안 비약적인 발전을 하였고 다양한 분야 및 산업에 영향을 주고 있다. 예술영역도 예외일 수는 없는데 본 논문에서는 시각예술·공학적 관점에서 2D 이미지를 3D로 창의적으로 생성하는 방법을 실험하고자 한다. 이를 위해 국내 아티스트 원본 이미지를 GAN 또는 Diffusion Models로 학습시킨 후 3D 변환 소프트웨어와 딥러닝을 활용하여 3D로 변환하고 그 결과를 선행연구 알고리즘과 비교 실험함으로써 2D to 3D 창의적 생성의 문제점과 개선점을 분석하고자 한다.

• 천문학회보
• /
• 제45권1호
• /
• pp.50.1-50.1
• /
• 2020

In this topic, I will introduce a recent work on reconstructing the cosmic density field based on the GAN. I will show the performance of the GAN compared to the traditional Unet architecture. I'd also like to discuss a 3-channels-based 2D datasets for the training to recover the 3D density field. Finally, I will present some performance tests based on the test datasets.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.667-669
• /
• 2022

2차원 이미지를 통한 자세 추정의 경우 관절이 겹치거나 가려져 있는 등의 인식 저해 요소로 인하여 자세 추정 정확도가 감소하는 한계가 있다. 본 논문에서는 GAN을 통해 2차원 이미지를 3차원으로 증강한 뒤 자세를 추정하는 기법을 제안한다. 제안하는 방법은 2차원 이미지의 평면좌표 값에서 GAN을 통해 노이즈 벡터 z축 값과 피사체에 투영되는 빛의 방향 값을 반영한 3차원 이미지를 만든다. 이러한 이미지 합성 과정을 거친 후 DeepLabCut을 사용해 관절 좌표를 추출하고 자세 추정 및 분류를 진행한다. 이를 통해 2차원에서의 자세 추정 정확도 향상을 기대할 수 있으며, 향후 이를 기반한 이상행동 탐지 분야에서 적용할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.