• 제목/요약/키워드: SinGAN

검색결과 26건 처리시간 0.028초

딥러닝 기반 단일 이미지 생성적 적대 신경망 기법 비교 분석 (Deep Learning-based Single Image Generative Adversarial Network: Performance Comparison and Trends)

  • 정성훈;공경보
    • 방송공학회논문지
    • /
    • 제27권3호
    • /
    • pp.437-450
    • /
    • 2022
  • 생성적 적대 신경망(GAN, Generative Adversarial Networks)는 이미지 생성 분야에서 주목할 만한 발전을 이루었다. 하지만 큰 데이터 셋에서 불안정한 모습을 보인다는 한계 때문에 다양한 응용 분야에 쉽게 적용하기 어렵다. 단일 이미지 생성적 적대 신경망은 한장의 이미지의 내부 분포를 잘 학습하여 다양한 영상을 생성하는 분야이다. 큰 데이터셋이 아닌 단 한장만 학습함으로써 안정적인 학습이 가능하며 이미지 리타겟팅, 이미지 조작, super resolution 등 다양한 분야에 활용 가능하다. 본 논문에서는 SinGAN, ConSinGAN, InGAN, DeepSIM, 그리고 One-Shot GAN 총 다섯 개의 단일 이미지 생성적 적대 신경망을 살펴본다. 우리는 각각의 단일 이미지 생성적 적대 신경망 모델들의 성능을 비교하고 장단점을 분석한다.

틱(Tic) 장애의 한의변증유형 설문지에 대한 신뢰도 및 요인분석 연구 (A Study on the Reliability and Factor analysis of Pattern Identification for Tic Disorders in children)

  • 위영만;이고은;정송화;이희경;유영수;강형원
    • 동의신경정신과학회지
    • /
    • 제23권1호
    • /
    • pp.59-82
    • /
    • 2012
  • Objectives : We purposed to objectify the pattern diagnosis of Tic disorders through factor and reliability analysis regarding a pattern identification questionnaire concerning Tic disorders in children. Methods : We chose and studied 144 children who were pattern-diagnosed out of 200 tic disordered children who visited H hospital in Seoul from January 2006 to April 2011. Results : 1. TTD (50%) was the most common type and the occurrence rate in male children was higher(4.76:1). Also, the rate of hospital visits was highest at the age 8(23.6%). 2. In results concering pattern diagnosis, Gan-poong-nae-dong was most frequently diagnosed in 53 patients (36.8%), and Dam-hwa-yo-sin (42 patients), Gan-sin-um-her (30 patients), and Bee-her-gan-wang (6 patients). 3. In an attempt to verify the reliability of the questionnaire, the coefficient regarding the whole questions (Cronbach ${\alpha}$) came to 0.909. Moreover, the reliability coefficient foreach sub factor was 0.687 in Ganpoong-nae-dong, 0.817 in Dam-hwa-yo-sin, 0.851 in Bee-her-gan-wang, and 0.726 in Gan-sin-um-her, respectively. Thus, their consistency was ensured. 4. In exploratory factor analysis concerning the most common five questions in the questionnaire, the questions of Dam-hwa-yo-sin and Gan-poong-nae-dong appeared to be part of different factors. While, Gan-sin-um-her and Bee-her-gan-wang questions showed that they belong to the same factors. 5. In factor analysis excluding both Gan-sin-um-her and Bee-her-gan-wang questions, both showed significant results; however, the one excluding Gan-sin-um-her showed improved results. Conclusions : From the above results concerning the Pattern Identification Questionnaire for Tic Disordered children, three separated patterns of Bee-her-gan-wang, Dam-hwa-yo-sin, Gan-poong-nae-dong are thought to be available for clinical use. However, further validity studies are needed.

SinGAN기반 데이터 증강과 random forest알고리즘을 이용한 고무 오링 결함 검출 시스템 (A rubber o-ring defect detection system using data augmentation based on the SinGAN and random forest algorithm)

  • 이용은;이한성;김대원;김경천
    • 한국가시화정보학회지
    • /
    • 제19권3호
    • /
    • pp.63-68
    • /
    • 2021
  • In this study, data was augmentation through the SinGAN algorithm using small image data, and defects in rubber O-rings were detected using the random forest algorithm. Unlike the commonly used data augmentation image rotation method to solve the data imbalance problem, the data imbalance problem was solved by using the SinGAN algorithm. A study was conducted to distinguish between normal products and defective products of rubber o-ring by using the random forest algorithm. A total of 20,000 image date were divided into transit and testing datasets, and an accuracy result was obtained to distinguish 97.43% defects as a result of the test.

SinGAN 딥러닝 모델을 이용한 넙치 질병 이미지 증강 (Image Augmentation of Paralichthys Olivaceus Disease Using SinGAN Deep Learning Model)

  • 손현승;최한석
    • 한국콘텐츠학회논문지
    • /
    • 제21권12호
    • /
    • pp.322-330
    • /
    • 2021
  • 수산 양식장에서 어류 질병을 초기에 발견하지 못하는 경우 밀폐된 공간 안에서 확산하기 때문에 집단 폐사로 이어질 확률이 매우 높다. 이런 이유로 질병의 조기 발견은 양식업에서 매우 중요하다. 양식장에서 질병의 확산을 막기 위해서는 초기에 병이 든 어류를 자동식별이 가능한 방법이 필요하다. 최근 딥러닝 기반의 어류 질병 자동식별 방법이 많이 사용되고 있는데, 어류의 질병 이미지가 충분하지 않아 객체 식별에 많은 어려움이 있다. 본 논문은 질병 자동식별 예측을 위한 질병 이미지의 부족 문제를 해결하기 위해서 SinGAN 딥러닝 모델을 이용하여 정상 이미지와 질병 이미지를 합성해 다양한 어류 질병 이미지를 자동 생성하는 방법을 제안한다. 넙치에서 가장 빈번히 발생하는 3가지 질병 스쿠티카병, 비브리오증, 림포시스티스에 대해서 SinGAN 기반으로 질병 이미지를 증강한다. 본 연구에서는 넙치 정상 이미지 11장에 각 질병 패턴 10가지를 합성하여서 스쿠티카병 110장, 비브리오증 110장, 림포시스티스 110장으로 총 330장을 만들었고 이를 통해 생성된 이미지는 4배수 하여 1,320장의 이미지를 생성할 수 있었다.

耳鳴의 原因別 分類 및 治法에 關한 文獻的 考察 (Literatural Consideration on the Classification of cause and Treatment of Tinnitus)

  • 이정용;노석선
    • 한방안이비인후피부과학회지
    • /
    • 제5권1호
    • /
    • pp.45-59
    • /
    • 1992
  • I have been studied the tinnitus. The results are summarized as follows. 1. The etiologies of tinnitus is classified the Zang fa endogenous factors of the Jong-Maek-Hae and exogenous factors of the Oun-Gi, in the Nei Ching. 2. In the endogenous factors the etiologies of the Zang fa is mostly hased deficiency of the kidney, which is concerned with Sim-Hae Gan-Darn-Hae and Bi-Wae-Hae, the etiologies of the phlegm fire is fire is divided into Sin-Hae, Om-Ju-Hu-Mi and No-Gi-Oaek-Sang. 3. The etiologies of the Jong-Maek-Hae is divided into deficiency of the stomach xu of both gi am blood and xu of the kidney. 4. In Nei ching,the etiologies of Oun-Gi divided into Gul-Eum-Pung-Mok and So-Yang-Sang-Hwa of the exgeous factors is regarded to wind and fire as following generations is regrded to wind the endogenous factors caused Sin-Hae Gi-Hae. 5. In the Nei ching, Since the O-Mi-Bo-Sa-Bub is uttered main treated of tinnitus is friquently used Bo-Sin Young-Sim-Sun-Gi and Choung-Gan-Sul- You1 as Zang-Fu Choung-Dam-Gang-Hwa as the Phlegm fire Bo-bi-Sin as the Jong Maek Hae and Gye-Pung-San-Hwa as the Oun-Gi.

  • PDF

Generative Adversarial Networks for single image with high quality image

  • Zhao, Liquan;Zhang, Yupeng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권12호
    • /
    • pp.4326-4344
    • /
    • 2021
  • The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

틱(Tic)장애(障碍)의 한의학적(韓醫學的) 이해(理解)에 관(關)한 문헌적(文獻的) 고찰(考察) (동의보감중심(東醫寶鑑中心)으로) (A study on Oriental-medical Understanding of Tic Disorders (Within Dong yui bo gam Book))

  • 심민;이종화;김태헌;류영수;강형원
    • 동의신경정신과학회지
    • /
    • 제18권2호
    • /
    • pp.1-12
    • /
    • 2007
  • Objective : The aim of this study was to categorize tic disorders and introduce the treatments of tic disorders in oriental medicine. This article includes the report of successful treatment with oriental medicine. Methods : The author classifided the terms of oriental medicine in associated with tic disorders based on DSM-IV and then studied symptoms, etiological causes, and treatment through ${\ll}$Dong yui bo gam Book${\gg}$ . Results and Conclusions : 1. The concept of Tic disorders is similar to Mok-cha (目箚), Gun-chuck-youk-soon, Soon-dong, Mae-hack-gi (梅核氣) and etc, in oriental medical term. 2. In oriental medicine, tic disorders can be classified Gan-poong-nae-dong-zung (肝風內動證) type, Dam-hwa-yo-sin-zung (淡火擾神證) type, Bee-her-gan-wang-zung (脾虛肝旺證) type and Gan-sin-um-her-zung (肝腎陰虛證) type. 3. In oriental medicine, tic disorders are treated by much(so) various therapy such as herb medication, acupuncture and moxibustion, oriental psychotherapy and dirigation (Gi-Gong, 氣功) etc. 4. Tourette’s disorder is not easy to cure. When the treatment of occidental medicine and that of oriental medicine are mutually cooperated, more effective medical care might be expected. Therefore, it is necessary for further study to treat tic disorders by mutually cooperated therapy.

  • PDF

19세기(世紀) 조선(朝鮮)의 수학(數學) 교과서(敎科書) (Mathematics Textbooks in the 19th Century Chosun)

  • 오채환;이상구;홍성사;홍영희
    • 한국수학사학회지
    • /
    • 제23권1호
    • /
    • pp.1-24
    • /
    • 2010
  • 정부기관인 학부(學部)에 의하여 새로운 학교제도가 1895년 조선에 도입되면서 이를 위한 교과서들이 출판되었다. 이 논문은 학부(學部)에서 최초로 출판된 수학 교과서인 간이사칙문제집(簡易四則問題集)(1895), 근이산술서(近易算術書)(1895), 학부의 의뢰로 이상설(李相卨)이 편찬한 산술신서(算術新書)(1900) 등 세 권을 조사하여 이들이 교과서의 역할과 함께 서양 수학이 조선에 들어오는 경로중의 하나를 이루게 된 것을 밝혀낸다. 근이산술서(近易算術書)와 산술신서(算術新書)는 20세기에 출판된 조선의 수학 교과서들에 많은 영향을 주었다.