• 제목/요약/키워드: Image abstraction

검색결과 75건 처리시간 0.032초

DSP(Digital signal proccesor)를 이용한 산업현장에서의 안전모 미착용 인식 기술 (Recognizing that a person doesn't put on a safety cap using DSP.)

  • 이용욱;송강석;정무일;임철후;문성모
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2009년도 추계학술대회
    • /
    • pp.530-533
    • /
    • 2009
  • 본 연구는 DSP(Digital signal processor)상에서 영상 처리 기술을 이용한 안전모 미착용 인식 기술을 개발한다. 이는 산업 현장에 배치된 영상 입력 장치를 통해 입력된 영상을 영상 처리하고, 안전모를 미착용한 사람이 발견될 경우 감독관에게 해당 인식 결과를 전송하여 조치를 취함으로써 만약의 사고 발생시 안전모를 착용하지 아니하여 발생할 수 있는 추가적인 인명피해를 미연에 방지한다. 안전모 미착용을 인식하기 위해서는 입력된 영상에서의 오브젝트 추출, 노이즈 제거, 사람/사물 판단, 머리 영역 추출, HSV 색공간을 이용한 안전모 착용 유/무 판단 등의 과정을 거친다. 영상입력 및 영상처리는 DSP를 이용해 처리하고 알고리즘의 속도 개선을 위하여 C언어 기반의 코드를 DSP가 제공하는 고유 함수(Intrinsics)들을 이용하여 최적화 한다.

  • PDF

멀티 스케일 레티넥스 기반의 얼굴 인식 (Face Detection Based On Multi-Scale Retinex)

  • 박성현;이준환;이상범
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2006년도 하계종합학술대회
    • /
    • pp.733-734
    • /
    • 2006
  • The Face Area Detection has an extensive error range of abstraction probabilities by image illuminations and background conditions. In this paper, to reduce error ranges of abstraction probabilities by factors such as illuminations and backgrounds, we made use of Retinex and the Face Area Detection algorithm together. In comparison with other previous methods[4], our proposed algorithm showed stabler and elevated detection rate.

  • PDF

Characterization on the Thermal Oxidation of Raw Natural Rubber Thin Film using Image and FT-IR Analysis

  • Kim, Ik-Sik;Cho, Hwanjeong;Sohn, Kyung-Suk;Choi, Hwa-Soon;Kim, Sung-Uk;Kim, Sinkon
    • Elastomers and Composites
    • /
    • 제55권1호
    • /
    • pp.51-58
    • /
    • 2020
  • In this study, the thermal oxidation of raw natural rubber (NR) was investigated under controlled conditions by optical image and fourier transform infrared (FT-IR) analysis. The thermal oxidation was performed on a transparent thin film of raw NR coated on a KBr window in a dark chamber at 80℃ under low humidity conditions to completely exclude moisture and restrict light oxidation. Images of the thin film of raw NR were obtained before and after thermal oxidation. FT-IR absorption spectra were measured in the transmission mode at different thermal exposure times. The thermal oxidation of NR was examined by the changes in the absorption peaks at 3449, 1736, 1447, 1377, 1242, 1072, and 833 cm-1, which corresponded to a hydroxyl group (-OH), a carbonyl group (-C=O) from an aldehyde and a ketone, a methylene group (-CH2-), a methyl group (-CH3), a carbon-oxygen single bond (-C-O) from an epoxide, a carbon-oxygen bond (-C-O) from an ether, an alcohol, a peroxide, or a cyclic peroxide, and a cis-methine group (cis-CCH3=CH-), respectively. In the initial stage of thermal oxidation, two different types of free radicals were produced quickly and randomly by the homolytic cleavage of a double bond and allylic hydrogen abstraction. Aldehydes and ketones were formed from chain scissions of the double bonds and alcohols were produced from allylic hydrogen abstraction at the methylene or methyl groups. Two reactions seemed to proceed competitively with each other. At a later stage, oxidative crosslinks seemed to dominate through the combination of free radicals such as an allyl radical (CH=CHCH2·), alkoxy radical (RO·), and peroxy radical (ROO·) and the reaction of a hydroperoxide (-ROOH) with a double bond. The image obtained after thermal oxidation showed hardening without cracks. Based on these observations, a plausible two-step mechanism was suggested for chain hardening caused by the thermal oxidation.

Single Image-Based 3D Tree and Growth Models Reconstruction

  • Kim, Jaehwan;Jeong, Il-Kwon
    • ETRI Journal
    • /
    • 제36권3호
    • /
    • pp.450-459
    • /
    • 2014
  • In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider tree-growing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local self-similarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease.

꼬뀔라의 의미분석망에 의한 폴 클레의 "매직 스퀘어" 연구 (A study of Paul Klee's by of Bernard Cocula)

  • 유재길
    • 조형예술학연구
    • /
    • 제1권
    • /
    • pp.63-93
    • /
    • 1999
  • This treatise begins with finding a meaning of Paul Klee's . It is pretty simpleto choose the square of Klee. The most important formative language for twenty century is abstraction. The element of speaking for abstraction issquare. The artists are trying to contain the nature and universe in the square. The role of magic square consisting with small squares of Klee is crystallized. The other side, the test of this study is a method analysis. The method analysis is changing while concept and style have been changing according to a period. The existing method analysis is an iconology used many times in Art history. This treatise introduces France symbolists, Bernard Cocula and Claude Peyroutet's analysis of a meaning of image(Semantique do l'image) who were applied to Modern Art. based on Iconography. It also applies to analysis of artwork of Klee. Cocula's is developed from one phase to five phase step by step. The first phase deals with an appearance of artwork. Subsequently, the second phase is directly adjacent to personal feeling and impression. This is an adequate method for image study in the analysis of modern arts. This phase makes it a rule to enjoy talking with artworks above all. The third phase begins with this question 'What do you see? (que voyons-nous?).' The applies exhaustively and strictly to complicated image artworks which need an elaborate analysis. It is very hard but audiences must try to maintain neutrality in front of artwork because cord formation and interpretation should be formed objectively. The meaning analysis and interpretation of the forth phase begins with this question 'what is the image rouse'(qu'evoque cote image?).' This phase is the most important in a process of symbolic analysis. The audience investigates personal elements and common elements. The fifth is synthetic analysis and interpretation phase. The synthesis is last phase and it reaches a valuation and a conclusion. Namely, the synthesis phase makes up synthesis conclusion, summarizes image character, and completes value adjudication. Sometimes it completes no conclusions in a silence. This study found a new possible analysis example from Paul Klee's work. The study emphasizes square analysis and interpretation and uses . The analysis of artwork by Cocula's is an example of the most important work of Klee's three artworks. The first analysis of artwork is and the second one is . The third one is . In these analyses, Klee usedmagic square 'to make natural pictorial element and to explain organic living things.'

  • PDF

SIFT를 이용한 내시경 영상에서의 특징점 추출 (Feature Extraction for Endoscopic Image by using the Scale Invariant Feature Transform(SIFT))

  • 오장석;김호철;김형률;구자민;김민기
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
    • /
    • pp.6-8
    • /
    • 2005
  • Study that uses geometrical information in computer vision is lively. Problem that should be preceded is matching problem before studying. Feature point should be extracted for well matching. There are a lot of methods that extract feature point from former days are studied. Because problem does not exist algorithm that is applied for all images, it is a hot water. Specially, it is not easy to find feature point in endoscope image. The big problem can not decide easily a point that is predicted feature point as can know even if see endoscope image as eyes. Also, accuracy of matching problem can be decided after number of feature points is enough and also distributed on whole image. In this paper studied algorithm that can apply to endoscope image. SIFT method displayed excellent performance when compared with alternative way (Affine invariant point detector etc.) in general image but SIFT parameter that used in general image can't apply to endoscope image. The gual of this paper is abstraction of feature point on endoscope image that controlled by contrast threshold and curvature threshold among the parameters for applying SIFT method on endoscope image. Studied about method that feature points can have good distribution and control number of feature point than traditional alternative way by controlling the parameters on experiment result.

  • PDF

패션 컬렉션에 나타난 번지는 이미지 문양의 염색기법과 조형미 (Dyeing Technique and Aesthetics of Diffusing Image Pattern in Fashion Collection)

  • 유현정
    • 한국의상디자인학회지
    • /
    • 제14권3호
    • /
    • pp.1-10
    • /
    • 2012
  • This study has purpose to understanding recent trends and image effect of textile in fashion by looking to dyeing technique and aesthetics of diffusing image pattern. Further the study will hope to provide basic data for fashion and textile designer fashion. The methods of this study are academic literatures as well as practical study through case studies about actual works. Dyeing techniques and aesthetics of diffusing image pattern since 2000 fashion collection and their results are as follows. First, Dyeing techniques of diffusing image pattern are wet-dyeing and printing. There are plangi dyeing, salt dyeing, alcohol dyeing and ikat dyeing in the wet-dyeing and spray dyeing, discharge dyeing in the printing. There are tie-dyeing, rumpling-dyeing and plank-dyeing in the plangi. Second, Forming of the diffusing image pattern are due to uneven seeping and the contingency of a chemical reaction by reducing the pressure and intensity. Third, Aesthetics of diffusing image pattern are extracted purity missing childhood, fantasy escaping facts of the situation and abstraction representing informal world from formative characteristics of diffusing image pattern.

  • PDF

물체의 3-D 형상 복원을 위한 삼각측량 시스템 (A Study on the 3-D Information Abstraction of object using Triangulation System)

  • 김국세;이정기;조애리;배일호;이준
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2003년도 춘계학술발표논문집 (상)
    • /
    • pp.409-412
    • /
    • 2003
  • The 3-D shape use to effect of movie, animation, industrial design, medical treatment service, education, engineering etc... But it is not easy to make 3-D shape from the information of 2-D image. There are two methods in restoring 3-D video image through 2-D image; First the method of using a laser; Second, the method of acquiring 3-D image through stereo vision. Instead of doing two methods with many difficulties, I study the method of simple 3-D image in this research paper. We present here a simple and efficient method, called direct calibration, which does not require any equations at all. The direct calibration procedure builds a lookup table(LUT) linking image and 3-D coordinates by a real 3-D triangulation system. The LUT is built by measuring the image coordinates of a grid of known 3-D points, and recording both image and world coordinates for each point; the depth values of all other visible points are obtained by interpolation.

  • PDF

An Iimage Association Technique Employing Constraints Among Pixels

  • Ishikawa, Seiji;Goda, Tomokazu;Kato, Kiyoshi
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 26-27 Oct. 1990
    • /
    • pp.951-956
    • /
    • 1990
  • The present paper describes a new technique for associating images employing a set of local constraints among pixels on an image. The technique describes the association problem in terms of consistent labeling which is an abstraction of various kinds of network constraints problems. In this particular research, a pixel and its gray value correspond to a unit and a label, respectively. Since constraints among units on an image are defined with respect to each n-tuple of pixels, performance of the present association technique largely depends on how to choose the n-tuples on an image plane. The main part of this paper is devoted to discussing this selection scheme and giving a solution to it as well as showing the algorithm of association. Also given are some results of the simulation performed on synthetic binary images to examine the performance of proposed technique, followed by the argument on further studies.

  • PDF

루이스 칸의 회화에 나타난 건축적 공간표현에 관한 연구 (A Study on the Presentation of Architectural Space in Painting of Louis I. Kahn)

  • 최영아;김주성;이강업
    • 한국실내디자인학회논문집
    • /
    • 제15권2호
    • /
    • pp.65-72
    • /
    • 2006
  • The purpose of this study is to show the development process of space concept by studying on the Louis I. Kahn's painting as pre-architectural thinking. Generally the idea of an architect is represented with lots of mediums, and the architectural thinking is developed through the process. In his early days, he, as an architect, made many travel sketches of Europe. In these clays, painting was the most significant medium to him. Since 1950's, he also left lots of sketches affected by abstract painting in addition to travel sketches. The results of this study were as follows: He found the image of antiquity from his painting and he made this image into abstraction in the facade. And the image of ruins was translated the layered space which was the transitional space. And he presented 'marche' through the series of painting of various view point. The Concept of 'marche' was translated into the connections of repetitive mass in the architectural space.