• Title/Summary/Keyword: Image-to-image Translation

Search Result 306, Processing Time 0.027 seconds

Night to day image translation with Generative Adversarial Network (Generative Adversarial Network 를 이용한 야간 도로 영상 보정 시스템)

  • Ahn, Namhyun;Kang, Suk-Ju
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2018.06a
    • /
    • pp.347-348
    • /
    • 2018
  • 본 논문에서는 야간 도로 영상을 보정하여 주간 영상으로 변환하는 알고리즘을 제안한다. 영상 변환 딥러닝 알고리즘인 Generative Adversarial Network(GAN)를 기반으로 주야간 도로 영상을 학습시켜 주야간 상호 변환이 가능한 시스템을 구현한다. 우선, 입력 영상에 대해 변환된 영상을 출력하는 generative network 를 정의한다. 또한, 변환된 영상을 다시 본래 영상으로 변환하는 inverse network 를 정의한다. Generative network 와 inverse network 를 모두 통과한 결과 영상과 본래 영상의 차 영상을 통해 손실 함수를 정의함으로써 파라미터를 목적에 맞게 학습시킬 수 있다. 또한, generative network 를 통과한 결과 영상과 목적하는 영상을 구분하는 discrimination network 를 정의하여 discrimination network 와 generative network 의 minimax two- player game 을 통해 변환된 영상이 실제 목적 영상과 유사하도록 유도한다. 제안하는 알고리즘을 적용하여 야간 도로 영상의 보정을 수행하면 주변 물체 인식이 어려운 야간 영상을 물체 인식이 용이한 주간 영상으로 변환 할 수 있다.

  • PDF

The First North Korean Painting in the Collection of the National Museum of Korea: Myogilsang on Diamond Mountain by Seon-u Yeong (국립중앙박물관 소장 산률(山律) 선우영(鮮于英) 필(筆) <금강산 묘길상도>)

  • Yi, Song-mi
    • MISULJARYO - National Museum of Korea Art Journal
    • /
    • v.97
    • /
    • pp.87-104
    • /
    • 2020
  • Myogilsang on Diamond Mountain, signed and dated (2000) by Seon-u Yeong (1946-2009), is the first work by a North Korean artist to enter the collection of the National Museum of Korea (fig. 1a). The donor acquired the painting directly from the artist in Pyeongyang in 2006. In consequence, there are no issues with the painting's authenticity.This painting is the largest among all existing Korean paintings, whether contemporary or from the Joseon Dynasty, to depict this iconography (see chart 1. A Chronological List of Korean Myogilsang Paintings.) It is ink and color on paper, measures 130.2 × 56.2 centimeters, and is in a hanging scroll format. Since this essay is intended as a brief introduction of the painting and not in-depth research into it, I will simply examine the following four areas: 1. Seon-u Yeong's background; 2. The location and the traditional appellation of the rock-cut image known as Myogilsang; 3. The iconography of the image; and 4) A comparative analysis of Seon-u Yeong's painting in light of other paintings on the same theme. Finally, I will present two more of his works to broaden the understanding of Seon-u Yeong as a painter. 1. Seon-u Yeong: According to the donor, who met Seon-u at his workshop in the Cheollima Jejakso (Flying Horse Workshop) three years before the artist's death, he was an individual of few words but displayed a firm commitment to art. His preference for subjects such as Korean landscapes rather than motifs of socialist realism such as revolutionary leaders is demonstrated by the fact that, relative to his North Korean contemporaries, he seems to have produced more paintings of the former. In recent years, Seon-u Yeong has been well publicized in Korea through three special exhibitions (2012 through 2019). He graduated from Pyeongyang College of Fine Arts in 1969 and joined the Central Fine Arts Production Workshop focusing on oil painting. In 1973 he entered the Joseon Painting Production Workshop and began creating traditional Korean paintings in ink and color. His paintings are characterized by intense colors and fine details. The fact that his mother was an accomplished embroidery specialist may have influenced on Seon-u's choice to use intense colors in his paintings. By 1992, he had become a painter representing the Democratic People's Republic of Korea with several titles such as Artist of Merit, People's Artist, and more. About 60 of his paintings have been designated as National Treasures of the DPRK. 2. The Myogilsang rock-cut image is located in the Manpok-dong Valley in the inner Geumgangsan Mountain area. It is a high-relief image about 15 meters tall cut into a niche under 40 meters of a rock cliff. It is the largest of all the rock-cut images of the Goryeo period. This image is often known as "Mahayeon Myogilsang," Mahayeon (Mahayana) being the name of a small temple deep in the Manpokdong Valley (See fig. 3a & 3b). On the right side of the image, there is an intaglio inscription of three Chinese characters by the famous scholar-official and calligrapher Yun Sa-guk (1728-1709) reading "妙吉祥"myogilsang (fig. 4a, 4b). 3. The iconography: "Myogilsang" is another name for the Bhodhisattva Mañjuśrī. The Chinese pronunciation of Myogilsang is "miaojixiang," which is similar in pronunciation to Mañjuśrī. Therefore, we can suggest a 妙吉祥 ↔ Mañjuśrī formula for the translation and transliteration of the term. Even though the image was given a traditional name, the mudra presented by the two hands in the image calls for a closer examination. They show the making of a circle by joining the thumb with the ring finger (fig. 6). If the left land pointed downward, this mudra would conventionally be considered "lower class: lower life," one of the nine mudras of the Amitabha. However, in this image the left hand is placed across its abdomen at an almost 90-degree angle to the right hand (fig. 6). This can be interpreted as a combination of the "fear not" and the "preaching" mudras (see note 10, D. Saunders). I was also advised by the noted Buddhist art specialist Professor Kim Jeong-heui (of Won'gwang University) to presume that this is the "preaching" mudra. Therefore, I have tentatively concluded that this Myogilsang is an image of the Shakyamuni offering the preaching mudra. There is no such combination of hand gestures in any other Goryeo-period images. The closest I could identify is the Beopjusa Rock-cut Buddha (fig. 7) from around the same time. 4. Comparative analysis: As seen in , except for the two contemporary paintings, all others on this chart are in ink or ink and light color. Also, none of them included the fact that the image is under a 40-meter cliff. In addition, the Joseon-period paintings all depicted the rock-cut image as if it were a human figure, using soft brushstrokes and rounded forms. None of these paintings accurately rendered the mudra from the image as did Seon-u. Only his painting depicts the natural setting of the image under the cliff along with a realistic rendering of the image. However, by painting the tall cliff in dark green and by eliminating elements on either side of the rock-cut image, the artist was able to create an almost surreal atmosphere surrounding the image. Herein lies the uniqueness of Seon-u Yeong's version. The left side of Seon-u's 2007 work Mount Geumgang (fig. 8) lives up to his reputation as a painter who depicts forms (rocks in this case) in minute detail, but in the right half of the composition it also shows his skill at presenting a sense of space. In contrast, Wave (fig. 9), a work completed one year before his death, displays his faithfulness to the traditions of ink painting. Even based on only three paintings by Seon-u Yeong, it seems possible to assess his versatility in both traditional ink and color mediums.

Deep Learning in Radiation Oncology

  • Cheon, Wonjoong;Kim, Haksoo;Kim, Jinsung
    • Progress in Medical Physics
    • /
    • v.31 no.3
    • /
    • pp.111-123
    • /
    • 2020
  • Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

Indian Traditional Clothing in Fashion Design of the 21st Century (2000년 이후 패션디자인에 나타난 인도 전통 복식)

  • Choi, Ho-Jeong
    • Journal of the Korean Society of Costume
    • /
    • v.56 no.9 s.109
    • /
    • pp.127-142
    • /
    • 2006
  • In this study, I have analyzed Indian traditional clothing in fashion design of 21st century by comparing 1,286 fashion items designed by Indian designers and 722 Western fashion items, which were presented from 2000 S/S to 2005 F/W Formal analysis were made for change in how to wear clothes, and change in items and ornaments. Change of traditional clothing was found in two ways; Western elements added to Indian tradition and Indian traditional image adopted in Western clothing. First, Indian traditional elements added to Western clothing in the formal aspect was found in 83% of Western collections and 27.2% of the Indian designers' collections. In Indian designers' collections, traditional clothing form takes 72.8%, which shows the regional characteristics of India where the traditional clothing is still adhered to in daily life especially by women. Second, from the fashion design of the Indian designers, we can find modernization of sari, change of traditional items into more active and modern way by adding Western clothing; change of form, color and material of traditional items in various ways; and decorative aspects highlighted by adding Indian traditional color, pattern or decoration into Western clothing. In most cases, Western collections are seasoned with Indian traditional image, rather than utilizing the form of Indian clothing. Although adopting the farm of Indian traditional clothing, it can be considered as a translation from the viewpoint of the West. Third, Indian look is expressed in various ways by reproducing Indian traditional ornaments such as earings, bracelets and henna, or by adopting Indian traditional fabric design and decoration in mufflers, bags and etc.

Solar farside magnetograms from deep learning analysis of STEREO/EUVI data

  • Kim, Taeyoung;Park, Eunsu;Lee, Harim;Moon, Yong-Jae;Bae, Sung-Ho;Lim, Daye;Jang, Soojeong;Kim, Lokwon;Cho, Il-Hyun;Choi, Myungjin;Cho, Kyung-Suk
    • The Bulletin of The Korean Astronomical Society
    • /
    • v.44 no.1
    • /
    • pp.51.3-51.3
    • /
    • 2019
  • Solar magnetograms are important for studying solar activity and predicting space weather disturbances1. Farside magnetograms can be constructed from local helioseismology without any farside data2-4, but their quality is lower than that of typical frontside magnetograms. Here we generate farside solar magnetograms from STEREO/Extreme UltraViolet Imager (EUVI) $304-{\AA}$ images using a deep learning model based on conditional generative adversarial networks (cGANs). We train the model using pairs of Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) $304-{\AA}$ images and SDO/Helioseismic and Magnetic Imager (HMI) magnetograms taken from 2011 to 2017 except for September and October each year. We evaluate the model by comparing pairs of SDO/HMI magnetograms and cGAN-generated magnetograms in September and October. Our method successfully generates frontside solar magnetograms from SDO/AIA $304-{\AA}$ images and these are similar to those of the SDO/HMI, with Hale-patterned active regions being well replicated. Thus we can monitor the temporal evolution of magnetic fields from the farside to the frontside of the Sun using SDO/HMI and farside magnetograms generated by our model when farside extreme-ultraviolet data are available. This study presents an application of image-to-image translation based on cGANs to scientific data.

  • PDF

Accuracy Improvement of DEM Using Ground Coordinates Package (공공삼각점 위치자료를 이용한 DEM의 위치 정확도 향상)

  • Lee, Hyoseong;Oh, Jaehong
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.3
    • /
    • pp.567-575
    • /
    • 2021
  • In order to correct the provided RPC and DEM generated from the high-resolution satellite images, the acquisition of the ground control point (GCP) must be preceded. This task is a very complicate that requires field surveys, GPS surveying, and image coordinate reading corresponding to GCPs. In addition, since it is difficult to set up and measure a GCP in areas where access is difficult or impossible (tidal flats, polar regions, volcanic regions, etc.), an alternative method is needed. In this paper, we propose a 3D surface matching technique using only the established ground coordinate package, avoiding the ground-image-location survey of the GCP to correct the DEM produced from WorldView-2 satellite images and the provided RPCs. The location data of the public control points were obtained from the National Geographic Information Institute website, and the DEM was corrected by performing 3D surface matching with this package. The accuracy of 3-axis translation and rotation obtained by the matching was evaluated using pre-measured GPS checkpoints. As a result, it was possible to obtain results within 2 m in the plane location and 1 m in height.

3D Object Extraction Mechanism from Informal Natural Language Based Requirement Specifications (비정형 자연어 요구사항으로부터 3D 객체 추출 메커니즘)

  • Hyuntae Kim;Janghwan Kim;Jihoon Kong;Kidu Kim;R. Young Chul Kim
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.9
    • /
    • pp.453-459
    • /
    • 2024
  • Recent advances in generative AI technologies using natural language processing have critically impacted text, image, and video production. Despite these innovations, we still need to improve the consistency and reusability of AI-generated outputs. These issues are critical in cartoon creation, where the inability to consistently replicate characters and specific objects can degrade the work's quality. We propose an integrated adaption of language analysis-based requirement engineering and cartoon engineering to solve this. The proposed method applies the linguistic frameworks of Chomsky and Fillmore to analyze natural language and utilizes UML sequence models for generating consistent 3D representations of object interactions. It systematically interprets the creator's intentions from textual inputs, ensuring that each character or object, once conceptualized, is accurately replicated across various panels and episodes to preserve visual and contextual integrity. This technique enhances the accuracy and consistency of character portrayals in animated contexts, aligning closely with the initial specifications. Consequently, this method holds potential applicability in other domains requiring the translation of complex textual descriptions into visual representations.

Cancellation of Motion Artifact in MRI (MRI에 있어서 체동 아티팩트의 제거)

  • Kim, Eung-Kyeu
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.37 no.3
    • /
    • pp.70-78
    • /
    • 2000
  • In this study, a new method for canceling MRI artifacts through the motion translation of image plane is presented Breathing often makes problems in a clinical diagnosis. Assuming that the head moves up and down due to breathing, rigid translational motions in only y(phase encoding axis) direction are treated Unlike the conventional Iterative phase retrieval algorithm, this method is based on the MRI imaging process and analyzing of Image property A new constraint condition with which the motion component and the true image component in the MRI signal can be separated by a simple algebraic operation is extracted After the x(read out) directional Fourier transformation of MRI signal is done, the y(phase encoding) directional spectrum phasing value is Just an algebraic sum of the Image component and the motion component Meanwhile, as It is known that the density of subcutaneous fat area is almost uniform in the head tomographs, the density distribution along a y directional line on this fat area is regarded as symmetric shape If the density function is symmetric, then the phase of spectrum changes linearly with the position Hence, the departure component from the linear function can be separated as the motion component Based on this constrant condition, the new method of artifact cancellation is presented Finally, the effectiveness of this algorithm IS shown by using a phantom with simulated motions.

  • PDF

Gendered innovation for algorithm through case studies (음성·영상 신호 처리 알고리즘 사례를 통해 본 젠더혁신의 필요성)

  • Lee, JiYeoun;Lee, Heisook
    • Journal of Digital Convergence
    • /
    • v.16 no.12
    • /
    • pp.459-466
    • /
    • 2018
  • Gendered innovations is a term used by policy makers and academics to refer the process of creating better research and development (R&D) for both men and women. In this paper, we analyze the literatures in image and speech signal processing that can be used in ICT, examine the importance of gendered innovations through case study. Therefore the latest domestic and foreign literature related to image and speech signal processing based on gender research is searched and a total of 9 papers are selected. In terms of gender analysis, research subjects, research environment, and research design are examined separately. Especially, through the case analysis of algorithms of the elderly voice signal processing, machine learning, machine translation technology, and facial gender recognition technology, we found that there is gender bias in existing algorithms, and which leads to gender analysis is required. We also propose a gendered innovations method integrating sex and gender analysis in algorithm development. Gendered innovations in ICT can contribute to the creation of new markets by developing products and services that reflect the needs of both men and women.

The Character Recognition System of Mobile Camera Based Image (모바일 이미지 기반의 문자인식 시스템)

  • Park, Young-Hyun;Lee, Hyung-Jin;Baek, Joong-Hwan
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.11 no.5
    • /
    • pp.1677-1684
    • /
    • 2010
  • Recently, due to the development of mobile phone and supply of smart phone, many contents have been developed. Especially, since the small-sized cameras are equiped in mobile devices, people are interested in the image based contents development, and it also becomes important part in their practical use. Among them, the character recognition system can be widely used in the applications such as blind people guidance systems, automatic robot navigation systems, automatic video retrieval and indexing systems, automatic text translation systems. Therefore, this paper proposes a system that is able to extract text area from the natural images captured by smart phone camera. The individual characters are recognized and result is output in voice. Text areas are extracted using Adaboost algorithm and individual characters are recognized using error back propagated neural network.