• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.430-436
• /
• 2022

본 논문에서는 다중 체온 감지용 지능형 카메라를 제안한다. 제안하는 카메라는 광학(4056*3040) 및 열화상(640*480) 2종의 카메라로 구성되고 획득된 영상으로부터 사람의 표정 및 체온을 분석하여 이상 증상을 감지한다. 광학 및 열화상카메라는 동시에 운영되며 광학 영상에서 객체를 검출한 후 얼굴영역을 도출하여 표정분석을 수행한다. 열화상카메라는 광학카메라에서 얼굴영역으로 판단한 좌표 값을 적용하고 해당영역의 최고 온도를 측정하여 화면에 표출한다. 이상 징후 감지는 분석된 표정 3가지(무표정, 웃음, 슬픔)와 체온 값을 활용하여 판단하며 제안된 장비의 성능을 평가하기 위해 광학영상 처리부는 Caltech, WIDER FACE, CK+ 데이터셋을 3종의 영상처리 알고리즘(객체검출, 얼굴영역 검출, 표정분석)에 적용하였다. 실험결과로 객체검출률, 얼굴영역 검출률, 표정분석률 각각 91%, 91%, 84%을 도출하였다.

• 비파괴검사학회지
• /
• 제6권2호
• /
• pp.37-45
• /
• 1987

Speckle photography is a very useful method for measuring in-plane surface displacement. In its basic form, the object to be studied is illuminated with a divergent laser beam, and a double exposure photograph of the object is recorded, on a fine-grain film or plate, before and after the object is deformed, The magnitude and the direction of the displacement can then be obtained by measuring the spacing and the direction of the Young's fringe, which is produced by probing the developed negative with an unexpaned laser beam, and consists of a pattern of parallel equi-spaced dark bands. In this paper, a hybrid optical and electronic image processing is described-Young's fringe on the viewing screen is observed by a TV-camera and the 2-D video signal is converted from analog to digital and transfered to the computer where the spacing and direction of the fringes are calculated. Several examples of application show that the displacement magnitude and direction can be determined with an accuracy of $0.1{\mu}m\;and\;0.1^{\circ}$ respectively.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.567-572
• /
• 2002

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS ). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 추계학술대회(한국공작기계학회)
• /
• pp.140-145
• /
• 2001

The equipment of industrial robot in manufacturing and assembly lines has rapidly increased. In order to achieve high productivity and flexibility, it becomes very important to develop the visual feedback control system with Off-Line Programming System(OLPS). We can save much efforts and time in adjusting robots to newly defined workcells by using Off-Line Programming System. A proposed visual calibration scheme is based on position-based visual feedback. The visual calibration system is composed of a personal computer, an image processing board, a video monitor, and one camera. The calibration program firstly generates predicted images of objects in an assumed end-effector position. The process to generate predicted images consists of projection to screen-coordinates, visible range test, and construction of simple silhouette figures. Then, camera images acquired are compared with predicted ones for updating position and orientation data. Computation of error is very simple because the scheme is based on perspective projection, which can be also expanded to experimental results. Computation time can be extremely reduced because the proposed method does not require the precise calculation of tree-dimensional object data and image Jacobian.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.5-8
• /
• 2001

We propose a realtime numeric caption recognition algorithm that automatically recognizes the numeric caption generated by computer graphics (CG) and displays the modified caption using the recognized resource only when a valuable numeric caption appears in the aimed specific region of the live sportscast scene produced by other broadcasting stations. We extract the mesh feature from the enhanced binary image as a feature vector after acquiring the sports broadcast scenes using a frame grabber in realtime and then recover the valuable resource from just a numeric image by perceiving the character using the neural network. Finally, the result is verified by the knowledge-based rule set designed for more stable and reliable output and is displayed on a screen as the converted CC caption serving our purpose. At present, we have actually provided the realtime automatic mile-to-kilometer caption conversion system taking up our algorithm f3r the regular Major League Baseball (MLB) program being broadcasted live throughout Korea over our nationwide network. This caption conversion system is able to automatically convert the caption in mile universally used in the United States into that in kilometer in realtime, which is familiar to almost Koreans, and makes us get a favorable criticism from the TV audience.

• 한국의류산업학회지
• /
• 제22권4호
• /
• pp.481-494
• /
• 2020

This study examined consumer perceptions and consumer responses of Halal cosmetics and compared them with vegan cosmetics, which is a term similarly used. Twitter API of Python 3.7 was used to collect the keywords '#halalcosmetics' and '#vegancosmetics'. First, the main perception of consumers on Halal cosmetics focused on the original concept, image, expected efficacy, and factors to consider before purchase, religious keywords, labels and packaging for Halal cosmetics. Second, the main consumer perception of vegan cosmetics was the product concept, expected efficacy, factors to consider before purchase, related vegan industry, image, and vegan cosmetic components. Third, the consumer perceptions of Halal cosmetics and vegan cosmetics were similar in multiple ways, and both concepts included the Cruelty-free concept. Fourth, consumer satisfaction factors included cosmetics color, brand's consumer service, efficacy, smell, packaging design, reasonable price, effects, and formulation of cosmetics as well as satisfaction with Halal certification, and satisfaction of Vegan consumers. Consumer dissatisfaction factors included smell, flavor, delay in shipping, dissatisfaction with formulation, discrepancy between actual color and computer screen, concern and distrust about the use of prohibited ingredients for Halal products. This study examined consumer perceptions and reactions to Halal and vegan cosmetics to create basic knowledge for niche markets that are emerging as an ethical beauty consumption trend.

• 한국항행학회논문지
• /
• 제17권3호
• /
• pp.346-353
• /
• 2013

소프트웨어 개발의 주요 동향 중 하나는 소프트웨어 산업의 세계화에 있다. 글로벌 소프트웨어 개발은 여러 가지 문제에 직면해 있다. 이러한 문제를 해결하기 위해 새로운 소프트웨어 개발 방법론과 프로세스가 필요하다. 최근 XP 동향에서의 개발 단계로 본다면 기존의 개발자와 개발자간의 협업을 위한 도구에서 벗어나 조직 구성원 전체가 협업할 수 있는 시스템이 필요하다. 텍스트 기반의 IDE 플러그인 형태나 단순한 화면공유, 채팅 기능을 제공하는 것이 아닌 구성원 전체가 협업할 수 있는 분산 페어 개발을 지원하는 시스템의 설계하고 개발하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.200-203
• /
• 2021

본 논문은 여러 인공지능 기술 중 이미지 분류를 통한 사람의 얼굴 표정을 인식하는 프로그램을 통해 사람의 표정을 인식하여 거울에 나타내는 스마트미러 기술을 소개한다. 여러 사람의 5가지 표정이미지를 통하여 인공지능으로 학습하였고, 사람이 거울을 볼 때 거울이 그 표정을 인식하여 인식한 결과를 거울에 나타내는 방식이다. 여러 사람의 얼굴을 표정별로 구분되어있는 dataset을 kaggle에서 제공하는 fer2013을 이용하여 사용하였고, 이미지 데이터 분류를 위해 네트워크 구조는 컨볼루션 신경망 구조를 이용하여 학습하였다. 최종적으로 학습된 모델을 임베디드 보드인 라즈베리파이4를 통해서 얼굴을 인식하여 거울을 통해 디스플레이에 나타내는 구조이다.

• Journal of the Optical Society of Korea
• /
• 제14권2호
• /
• pp.152-162
• /
• 2010

This study examined the effects of surround luminance on the shape of the spatial luminance contrast sensitivity function (CSF). The reduction in brightness of uniform neutral patches shown on a computer controlled display screen is also assessed to explain the change of CSF shape. Consequently, a large amount of reduction in contrast sensitivity at middle spatial frequencies can be observed; however, the reduction is relatively small for low spatial frequencies. In general, the effect of surround luminance on the CSF appears similar to that of mean luminance. Reduced CSF responses result in less power of the filtered image; therefore, the stimulus should appear dimmer with a higher surround luminance.

• 산업공학
• /
• 제10권1호
• /
• pp.223-235
• /
• 1997

The process of determining the optimal tool path in PCB(printed circuit board) drilling operations is identical with that of solving a TSP(traveling salesman problem). However, the optimal solution will be ruined when a drill bit needs tracking back in its tool paths. The back tracking occurrences shorten a life of the main spindle and result in inaccurate mechanical movements. In this study, the performances of four heuristics(Nearest Neighbor, Convex Hull, Greatest Angle and Most Eccentric Ellipse) are evaluated to obtain feasible tool paths along with less number of back trackings for a large number of holes(more than 2000holes/bit) and to generate corresponding NC codes for a given CNC drill. Also, the operations of these algorithms are visualized to show a user the graphic image of tool visitation with PCB holes on a computer screen.