• 제목/요약/키워드: CycleGAN

검색결과 53건 처리시간 0.024초

Ship Number Recognition Method Based on An improved CRNN Model

  • Wenqi Xu;Yuesheng Liu;Ziyang Zhong;Yang Chen;Jinfeng Xia;Yunjie Chen
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제17권3호
    • /
    • pp.740-753
    • /
    • 2023
  • Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

순환 적대적 생성 신경망을 이용한 안면 교체를 위한 새로운 이미지 처리 기법 (A New Image Processing Scheme For Face Swapping Using CycleGAN)

  • 반태원
    • 한국정보통신학회논문지
    • /
    • 제26권9호
    • /
    • pp.1305-1311
    • /
    • 2022
  • 최근 모바일 단말기 및 개인형 컴퓨터의 비약적인 발전과 신경망 기술의 등장으로 영상을 활용한 실시간 안면 교체가 가능해졌다. 특히, 순환 적대적 생성 신경망은 상호 연관성이 없는 이미지 데이터를 활용한 안면 교체가 가능하게 만들었다. 본 논문에서는 적은 학습 데이터와 시간으로 안면 교체의 품질을 높일 수 있는 입력 데이터 처리 기법을 제안한다. 제안 방식은 사전에 학습된 신경망을 통해서 추출된 안면의 특이점 정보와 안면의 구조와 표정에 영향을 미치는 주요 이미지 정보를 결합함으로써 안면 표정과 구조를 보존하면서 이미지 품질을 향상시킬 수 있다. 인공지능 기반의 무참조 품질 메트릭 중의 하나인 blind/referenceless image spatial quality evaluator (BRISQUE) 점수를 활용하여 제안 방식의 성능을 정량적으로 분석하고 기존 방식과 비교한다. 성능 분석 결과에 따르면 제안 방식은 기존 방식 대비 약 4.6%~14.6% 개선된 BRISQUE 점수를 나타내었다.

조경종옥탕가미방으로 호전된 다낭성난소증후군에 의한 희발월경 환자 증례 보고 (Case Report of Patients of Oligomenorrhea due to Polycystic Ovarian Syndrome Improved by Jokyeongjongok-tang-gami)

  • 김민욱;김보리;감은영;양승정;조성희
    • 대한한방부인과학회지
    • /
    • 제33권3호
    • /
    • pp.175-186
    • /
    • 2020
  • Objectives: The purpose of this study is to report the effect of Jokyeongjongok-tang-gami in case of oligomenorrhea patients classified with gan-ulgiche and eumheo due to polycystic ovary syndrome. Methods: Three patients suffering from oligomenorrhea due to polycystic ovary syndrome were treated with korean medical treatment (herbal medicine, moxibustion, acupuncture) more than 3 months. The patients classified with gan-ulgiche and eumheo were treated with Jokyeongjongok-tang-gami. Results: Three oligomenorrhea patients recovered normal menstrual cycle more than 3 times after taking Korean medical treatment for 3~6 months. Conclusions: This 3 cases classified with gan-ulgiche and eumheo show Jokyeongjongok-tang-gami is effective on patients with rare menstruation due to polycystic ovary syndrome.

Vehicle Detection at Night Based on Style Transfer Image Enhancement

  • Jianing Shen;Rong Li
    • Journal of Information Processing Systems
    • /
    • 제19권5호
    • /
    • pp.663-672
    • /
    • 2023
  • Most vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.

The Relationship Between Financial Condition and Business Cycle in Mongolia

  • Doojav, Gan-Ochir;Purevdorj, Munkhbayar
    • East Asian Economic Review
    • /
    • 제23권2호
    • /
    • pp.203-223
    • /
    • 2019
  • This paper examines the interactions between financial conditions and business cycles in Mongolia, a small open economy, heavily depending on commodity exports. We construct two financial conditions indexes based on the reduced form IS model and the vector autoregression (VAR) model as surveillance tools to quantify the degree of the financial conditions. We find that real short-term interest rate and real effective exchange rate gap get a higher weight in the FCIs. Both business and financial cycles are often more pronounced in Mongolia, and financial condition is dependent of the financial and monetary policies in place. The analysis of the predictive power of the FCIs for business cycles shows that they have predictive information for the near-term economic activities. FCIs are also helpful in signaling inflation turning points.

딥러닝 학습을 이용한 한글 글꼴 자동 제작 시스템에서 글자 쌍의 매핑 기준 평가 (Evaluation of Criteria for Mapping Characters Using an Automated Hangul Font Generation System based on Deep Learning)

  • 전자연;지영서;박동연;임순범
    • 한국멀티미디어학회논문지
    • /
    • 제23권7호
    • /
    • pp.850-861
    • /
    • 2020
  • Hangul is a language that is composed of initial, medial, and final syllables. It has 11,172 characters. For this reason, the current method of designing all the characters by hand is very expensive and time-consuming. In order to solve the problem, this paper proposes an automatic Hangul font generation system and evaluates the standards for mapping Hangul characters to produce an effective automated Hangul font generation system. The system was implemented using character generation engine based on deep learning CycleGAN. In order to evaluate the criteria when mapping characters in pairs, each criterion was designed based on Hangul structure and character shape, and the quality of the generated characters was evaluated. As a result of the evaluation, the standards designed based on the Hangul structure did not affect the quality of the automated Hangul font generation system. On the other hand, when tried with similar characters, the standards made based on the shape of Hangul characters produced better quality characters than when tried with less similar characters. As a result, it is better to generate automated Hangul font by designing a learning method based on mapping characters in pairs that have similar character shapes.

인터랙티브 미디어 플랫폼 콕스에 제공될 4가지 얼굴 변형 기술의 비교분석 (Comparison Analysis of Four Face Swapping Models for Interactive Media Platform COX)

  • 전호범;고현관;이선경;송복득;김채규;권기룡
    • 한국멀티미디어학회논문지
    • /
    • 제22권5호
    • /
    • pp.535-546
    • /
    • 2019
  • Recently, there have been a lot of researches on the whole face replacement system, but it is not easy to obtain stable results due to various attitudes, angles and facial diversity. To produce a natural synthesis result when replacing the face shown in the video image, technologies such as face area detection, feature extraction, face alignment, face area segmentation, 3D attitude adjustment and facial transposition should all operate at a precise level. And each technology must be able to be interdependently combined. The results of our analysis show that the difficulty of implementing the technology and contribution to the system in facial replacement technology has increased in facial feature point extraction and facial alignment technology. On the other hand, the difficulty of the facial transposition technique and the three-dimensional posture adjustment technique were low, but showed the need for development. In this paper, we propose four facial replacement models such as 2-D Faceswap, OpenPose, Deekfake, and Cycle GAN, which are suitable for the Cox platform. These models have the following features; i.e. these models include a suitable model for front face pose image conversion, face pose image with active body movement, and face movement with right and left side by 15 degrees, Generative Adversarial Network.

GAN을 이용한 흑백영상과 위성 SAR 영상간의 모의 및 컬러화 (Simulation and Colorization between Gray-scale Images and Satellite SAR Images Using GAN)

  • 조수민;허준혁;어양담
    • 대한토목학회논문집
    • /
    • 제44권1호
    • /
    • pp.125-132
    • /
    • 2024
  • 광학 위성영상은 국가 보안 및 정보 획득을 목적으로 사용되며 그 활용성은 증가하고 있다. 그러나, 기상 조건 및 시간의 제약으로 사용자의 요구에 적합하지 않은 저품질의 영상을 획득하게 된다. 본 논문에서는 광학 위성영상의 구름 폐색영역을 모의하기 위하여 고해상도 SAR 영상을 참조한 딥러닝 기반의 영상변환 및 컬러화 모델을 생성하였다. 해당 모델은 적용 알고리즘 및 입력 데이터 형태에 따라 실험하였으며 생성된 모의영상을 비교 분석하였다. 특히 입력하는 흑백영상과 SAR 영상간의 화소값 정보량이 유사하도록 하여 상대적으로 색상정보량 부족에서 오는 문제점을 개선하였다. 실험 결과, Gray-scale 영상과 고해상도 SAR 영상으로 학습한 모의영상의 히스토그램 분포가 비교적 원 영상과 유사하였고, 정량적인 분석을 위하여 산정한 RMSE 값은 약 6.9827, PSNR 값은 약 31.3960으로 나타났다.

옥천지향사대(沃川地向斜帶)의 진화(進化)와 광화작용(鑛化作用) (Evolution and Mineralizations in the Ockcheon Geosynclinal Zone)

  • 윤석규
    • 자원환경지질
    • /
    • 제4권2호
    • /
    • pp.77-90
    • /
    • 1971
  • About four hundred deposits of iron, talc, fluorite, tungsten, molybdenum, lead, zinc and other polymetallic mineral deposits were plotted on the Ore Distribution Map of the Ockcheon Geosynclinal Area. These mineral deposits plotted on the map can be divided into the several metallogenic zones by the consideration of their geologic background including the sedimentary and tectonic cycles and the igneous activities in the geosynclinal evolution, as follows: a. Chungju iron and talc zones. b. Cheong-san copper bearing iron sulphide zone c. Kumsan-Muju fluorite-polymetallic zones. d. Cheong-an Puyong and Ein Suckseong gold zone e. Hwang-gan Seolcheon and Sangju gold zones. Chungju iron zone originated in the iron bed in the Kemyongsan Series corresponding to the Pre-Ockcheon Cycle of evolution history. In early period of the Ockcheon Cycle, Hyangsanri quartzite and Munjuri phyllitic formation corresponding to the lower terrigenous sequence were not mineralized while the next sequence of the Samsungsan basic igneous-metamorphic formation and the Changri limestone formation were mineralized by the copper bearing iron sulphide and the fluorite-polymetallic deposits respectively. Two generations of the gold zones are recognized. The earlier generation distributes directionaly in the outside of the Ockcheon sedimentary belt was followed by the earlier grantitic invasion of Jurasic in age, while the later generation scatters at random which was related to the nondirectional Cretaceous granitic intrusion of the Post-Ockcheon Cycle. Conclusively speaking, it was disclosed that the endogenic mineralization in the Ockcheon geosyn clinal zone was not conspicuous in its inner sedimentary belt except its limestone area but in its outer peripheral granitic or gneissic zones, and the related igneous activities occured in the Post-Ockcheon Cycle of evolution history.

  • PDF

Fabrication of EDM Electrodes by Localized Electrochemical Deposition

  • Habib, Mohammad Ahsan;Gan, Sze Wei;Lim, Han-Seok;Rahman, Mustafizur
    • International Journal of Precision Engineering and Manufacturing
    • /
    • 제9권2호
    • /
    • pp.75-80
    • /
    • 2008
  • The fabrication of complex three-dimensional electrodes for micro electrical discharge machining (micro-EDM) is an important issue in the field of micromachining Localized electrochemical deposition (LECD) is a simple and inexpensive technique for fabricating micro-EDM electrodes. This study presents a new process for manufacturing electrodes with complex cross-sections using masks of different shapes, In this process, a non-conductive mask is placed between an anode and cathode that are immersed in a plating solution of acidified copper sulfate. The LECD is achieved by applying a pulsed voltage between the anode and cathode, which are separated by a small distance. In this setup, the cathode is placed above the anode and the mask, so that the deposited electrode can be used directly for EDM without changing the tool orientation. We found that the microstructure of the deposited electrode is influenced by the concentration of the plating solution and organic additives. Moreover, the values of the voltage, frequency, and duty cycle of the pulsed input have significant effects on the microstructure of the fabricated electrode. Finally, the optimum values of the voltage, frequency, and duty cycle were determined for the most effective fabrication of complex-shaped electrodes.