• 제목/요약/키워드: Nature Scene Image

검색결과 21건 처리시간 0.022초

스테레오 영상 해석 과정의 가려진 영역 검출에 관한 연구 (Research about the occlusion area detection though it is a stereo Image analysis)

  • 이한구;우동민
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
    • /
    • pp.144-146
    • /
    • 2004
  • Stereo image analysis has been an important tool for reconstructing 3D terrain. By In its nature, occlusion is one of difficulties we cannot avoid in stereo matching. This paper presents a study on occlusion detection by employing LRC(Left-Right Check) and OCC(Occlusion Constraint). Experimental results show that these method can effectively detect occluded regions and those regions are usually occurred around object contours and scene discontinuity.

  • PDF

Deep-Learning Approach for Text Detection Using Fully Convolutional Networks

  • Tung, Trieu Son;Lee, Gueesang
    • International Journal of Contents
    • /
    • 제14권1호
    • /
    • pp.1-6
    • /
    • 2018
  • Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.

John Galliano 작품에 표현된 웃음의 미학 (The Comic Expression depicted on John Galliano's Works)

  • 장애란
    • 복식
    • /
    • 제56권3호
    • /
    • pp.129-142
    • /
    • 2006
  • The historicism and romanticism of John Galliano's designs are rivaled only by the spectacular and theatrical nature of his fashion shows; romantic silhouette, the complexity of the cut and, of course, the painstaking attention to historical detail. Galliano's approach is very much that of a British designer in that he absorbs wildly diverging historical and cultural elements to invent new hybridizations of the contemporary. Galliano started his career as part of the wildly uninhibited avant-garde London design scene. His designs were twisted and artfully torn, weired and also beautiful. The purpose of this study is to investigate the Comic Expression depicted on John Galliano's works by borrowing the Comic. The Comic or the Comedy is a kind of art form that signifies exciting effects, and so, is a means of raising a laugh. The similar concepts of the Comic already were depicted by means of transformation and distortion of form, satire, fantastic pastiche and reversion of substances on Cubism, Dada, Surrealism, Pop Art and Postmodernism. Therefore, John Galliano selected the quixotic expressional methods to seek for having playful fun. The aesthetics of the Comic is the beauty based on quantitative or qualitative contradiction between expectations and realizations. That is, the Comic is characterized by getting rid of stress through laugh with clarifying a subject of contradiction. This study found that John Galliano's designs are expressed the quixotic comic on Historical image, Exotic image and Primitive image to make a complaint against the social evils.

다중 단계 신호의 적응적 전파를 통한 동일 장면 영상의 이원 영역화 (Bilayer Segmentation of Consistent Scene Images by Propagation of Multi-level Cues with Adaptive Confidence)

  • 이수찬;윤일동;이상욱
    • 방송공학회논문지
    • /
    • 제14권4호
    • /
    • pp.450-462
    • /
    • 2009
  • 최근까지 단일 영상이나 동영상을 영역화하는 기법들은 다양하게 제시되어 왔으나, 유사한 장면에 대한 여러 장의 영상을 동시에 영역화하는 기법은 많지 않았다. 본 논문에서는 한 장소에서 연속적으로 촬영하였거나 전경 물체가 유사한 여러 영상들을 동일 장면 영상으로 정의하고, 이런 동일 장면 영상들을 적은 양의 사용자 입력을 통해 효과적으로 영역화하는 기법을 제안한다. 구체적으로, 사용자가 최초의 영상 한 장을 직접 영역화한 후, 그 영상의 영역화 결과와 영상의 특성을 토대로 다중 단계 신호를 적응적 가중치를 주어서 인접 영상으로 전파하고, 이를 통해 제안하는 기법은 인접 영상을 반복적으로 영역화한다. 영역화는 마르코프 랜덤 장에서의 에너지 최소화를 통해 이루어지는데, 전파되는 신호는 각 픽셀에 대한 에너지를 정의하는 바탕이 되며, 픽셀, 픽셀 패치, 그리고 영상 전체로부터 비롯되었는가에 따라 낮은 단계, 중간 단계, 그리고 높은 단계의 신호로 지칭된다. 또한 에너지 최소화 틀 안에서 전파된 신호를 통해 정의되는 에너지 역시 낮은 단계, 중간 단계, 그리고 높은 단계의 세 단계로 정의한다. 이런 과정을 통해 전파된 신호를 최대한 다양하게 활용하고, 이를 통해 다양한 영상에 영역화 결과가 일관되게 유지된다. 다양한 동일 장면 영상들에 제안하는 기법을 적용하여 성능을 평가하고, 픽셀 패치를 바탕으로 하는 중간 단계 신호만을 이용한 결과와 제안하는 다중 신호를 적용하는 기법의 결과를 비교한다.

Segment-based Image Classification of Multisensor Images

  • Lee, Sang-Hoon
    • 대한원격탐사학회지
    • /
    • 제28권6호
    • /
    • pp.611-622
    • /
    • 2012
  • This study proposed two multisensor fusion methods for segment-based image classification utilizing a region-growing segmentation. The proposed algorithms employ a Gaussian-PDF measure and an evidential measure respectively. In remote sensing application, segment-based approaches are used to extract more explicit information on spatial structure compared to pixel-based methods. Data from a single sensor may be insufficient to provide accurate description of a ground scene in image classification. Due to the redundant and complementary nature of multisensor data, a combination of information from multiple sensors can make reduce classification error rate. The Gaussian-PDF method defines a regional measure as the PDF average of pixels belonging to the region, and assigns a region into a class associated with the maximum of regional measure. The evidential fusion method uses two measures of plausibility and belief, which are derived from a mass function of the Beta distribution for the basic probability assignment of every hypothesis about region classes. The proposed methods were applied to the SPOT XS and ENVISAT data, which were acquired over Iksan area of of Korean peninsula. The experiment results showed that the segment-based method of evidential measure is greatly effective on improving the classification via multisensor fusion.

A Multimedia Tutorial system for Learning the French Language

  • Jho, Gook-Hyung;Jang, Jae-Hyuk;Sim, Gab-Sig
    • 한국컴퓨터정보학회논문지
    • /
    • 제21권1호
    • /
    • pp.191-198
    • /
    • 2016
  • This paper aims to present how to design and implement a multimedia tutorial system for the self-learning French language using Director with additional tools. To implement a multimedia tutorial system we need to design several steps. First, we should choose the level of the users and design tutorial. Second, we should prepare all materials such as sounds, graphics, text and video. Finally, we should implement the selected elements and control the educational software. Due to the nature of the paper, it must emphasize French basic conversation to make environment that be used in each scene and the scene of the context dialog. In view of the fact that the fitness of each content utilization field of multimedia authoring tool is high, it is possible as part of the system sizing process of the manufacturing process, to impart its meaning. This learning-contents are composed of 10 units each situation, and we anticipate there are the several effects of this system on basic French students. This system helps lecturer get French students interested in lessons, and enables learner to learn French of the role of iterative practice by linking image and sound. Also this system helps learners to prepare and review French studying after a lesson and allows leaners to maximize their efficiency. The future of this work is to implement this system on the app.

20세기말 패션 디자인에 나타난 신표현주의적 이미지에 관한 연구

  • 이효진
    • 복식
    • /
    • 제40권
    • /
    • pp.5-23
    • /
    • 1998
  • The main purpose of this study was intended to analyze the image of N대-Expressionism represented in the late of 20th century fashion design. By the late 1960s and the early 1970s. the prevailing notion of modernity, which had pushed the limits of art beyond previous boundaries, had begun to lose its urgency. Critics called the new pluralistic era which the West was entering Post-Modern. Furthermore, the predominance of America and the New York scene is diminishing, and artistic leadership is now international. Post-Modernism dialectcally made denial of Modernism as likely as New Image Painting and Decorative Pattern Painting Art in 1970's and it was availed as a dialectcal means for the pre-diction of new comings that would be appeared at painting art in 1980's. New Image Painting has been called as Neo-Expressionism. The N대-Expressionists selected human's feature because appeared flankly, directly irregular agitation in the visual effect and they believed human's destructive and amputate body was cruelty. So they express it on the surface canvas. Under the these background, the image of Neo-Expressionism was represented in the late of 20th century fashion design such as the upside-down image of human feature, the image as ameditation on German myth and history, culture, the ecletic image is made of use a mixture of material. The properties of composition, line, color, texture, and form, common to all plastic art, are now more readily recognized and historically valued in every work. That is, individuality, humanity, and the human condition have been at the core of most Western art and Fashion design. Especially Fashion design has been one of the principal instruments used to examine our nature and to promote the notion of growth, self-understanding, and change.

  • PDF

SURF 알고리즘을 이용한 파노라마 영상 재구성 (Panoramic Image Reconstruction using SURF Algorithm)

  • 김광백
    • 한국컴퓨터정보학회논문지
    • /
    • 제18권4호
    • /
    • pp.13-18
    • /
    • 2013
  • 디지털 카메라의 보급으로 카메라만 있으면 누구나 손쉽게 파노라마 사진을 찍을 수 있다. 파노라마 사진이란 카메라를 삼각대에 고정시킨 후, 일부분을 중첩시키면서 회전하여 얻어진 이미지를 수평으로 이동하여 이미지를 결합시키는 사진이다. 이때 수동으로 사진을 찍을 경우에는 각도가 틀어져 겹쳐지는 부분을 자연스럽게 정합하기 어렵다. 기존의 방법에서는 라벨링을 이용하여 객체를 비교한 후에 결합시키는 방법을 적용하였으나 시간이 많이 소요되고 각각의 이미지를 라벨링하는 과정에서 개체 간의 불일치가 발생하여 정확히 영상을 결합할 수 없는 경우가 발생한다. 따라서 본 논문에서는 처리 속도 개선을 위하여 전체 이미지의 1/3만 라벨링한 후에 객체 간을 비교하여 결함시킨다. 그리고 각도가 틀린 경우에는 특징점을 찾아내는 SURF 알고리즘을 적용하여 각각의 이미지에서 라벨링한 사각형의 4개의 포인터에 대해 1개의 중심점을 구하여 호모그래피를 이용하여 2개의 영상을 자연스럽게 정합한다. 본 논문에서 제안한 파노라마 영상 재구성 방법의 성능을 평가하기 위하여 다양한 이미지를 대상으로 실험한 결과, 기존의 방법보다 영상을 재구성하는데 효과적인 것을 확인하였다.

남원시의 도시경관에 대한 시각과 청각의 이미지구조와 인지특성 (The Visual and Auditory Images and Cognitive Characteristics on the Townscapes in Namwon City)

  • 한명호;오양기
    • KIEAE Journal
    • /
    • 제8권2호
    • /
    • pp.11-21
    • /
    • 2008
  • The purpose of this study is to interpret the visual and auditory images and cognitive characteristics about townscapes in Namwon city. It was acquired the survey results about 8 types of verbal interviews and 2 kinds of sketch maps which are based on urban images from 102 Namwon residents. They held in a variety of images of Namwon in their minds such as Jiri mountain, clean environment, sightseeing, special products, urban/building structures, Korean classical music, historical novel, local sports, and emotional images. The nice streets or places which the residents recommended are the places which have abundant natural areas, psychological peace and rest, available space for physical activity, places for performances and events, and regional attractions. The streets or places which they didn't like are decadent places, and areas of crowded traffic. The transition times of visual and auditory scene can be classified with the Saemaul movement in the 1970's(the rural new community movement) and the improvement of the city in the 1990's. The elements of visual images in Namwon city on the basis of the cognitive maps were expressed such elements as paths, districts, nodes, edges, and landmarks. The elements of auditory images, which are on the basis of the concept of the soundscape, included sounds of narrative musical form unique to Korea; p'ansori, sounds of traditional markets, and sounds of nature. It was found that the imageability of visual and auditory images is relatively clear in specific areas in Namwon city.

"그림 같은 풍경"의 재해석 - 병산서원 차경 설계의 수양론(修養論)적 해석 - (Reimagining "A Picturesque Landscape" - The Borrowed Scenery of the Byungsan Neo-Confucian Academy, Korea, and its Heuristic Instrumentality -)

  • 이경근
    • 한국조경학회지
    • /
    • 제50권6호
    • /
    • pp.15-29
    • /
    • 2022
  • 병산서원은 한국 전통 건축과 차경 설계의 자연친화성 또는 비인위성을 대표하는 아이콘으로 인식되고 있다. 본 연구는 오늘날 병산서원을 수식하는 대표적인 비유인 '그림과 액자'를 중심으로 서원의 차경이 착시와 환영의 풍경을 선사하는 인위적 기법임을 논의하고자 한다. 연구는 다음의 세 부분으로 구성된다. 첫째, 오늘날 '그림'과 '액자'는 각기 순수한 자연의 아름다움과 이를 여과 없이 전달하는 건축적 틀을 일컫는 비유로 사용되며, 이는 자연과 건축의 조화라는 현대 한국인의 기대 심리가 투사된 결과물임을 지적한다. 둘째, 서원을 설계하고 이용하던 조선 중기의 인물들이 차경을 향유한 방식을 추론하기 위해 당대의 시와 회화에 묘사된 풍경과 차경이 선사하는 풍경을 비교하고, 차경을 통한 조망이 동시대의 경관 예술과 마찬가지로 성리학적으로 이념화된 자연의 이미지를 연상하도록 유도함을 밝힌다. 셋째, 이상의 고찰을 바탕으로 차경이 선사하는 '그림'이란 보는 이의 인식이 빚어낸 환영(幻影)이며 차경이라는 '액자'는 이를 촉발하는 인지적 착시 기법으로 구성되어 있음을 주장한다. 이상의 논의를 통해 병산서원의 차경을 자연주의적 표상으로 소비하는 시선에서 이탈하여 시대적, 문화적 보기 방식을 유도하는 적극적인 설계 행위로 인식하고, 자연과 문화유산을 바라보는 오늘날의 시선을 재점검하는 계기를 마련하고자 한다.