• Restorative Dentistry and Endodontics
• /
• 제23권2호
• /
• pp.575-585
• /
• 1998

Use of the digital camera as a color measuring device was proposed. Digital camera can save, adjust and transmit image using computer. But it has great disadvantage that color of image possibly altered by environment of image capturing state, so the color reproducibility of digital camera can severly damage, Casmatch, the supplement for color correction, was proposed for enhance the color reproducibility of digital camera. Thus for study the efficacy of the Casmatch in enhancing the color reproducibility of digital camera, image of 78area in 39teeth was captured three times during two days and color reproducibility was evaluated and analyzed in terms of the use of Casmatch, teeth positions, and area within the tooth and comparatively analyzed. Results were as follow ; 1. ${\Delta}$E the color reproducibility of digital camera was 6.90${\pm}$3.27 in same day and 7.43${\pm}$3.94 in different day, and the color reproducibility when using Casmatch correction was 6.21${\pm}$3.86, 7.59${\pm}$4.48, there is no enhancement in using Casmatch correction. 2. There is no difference in color reproducibility between teeth, but color reproducibility of the middle third was greater(p<0.05) than the gingival third before color correction using Casmatch.

• 한국멀티미디어학회논문지
• /
• 제5권2호
• /
• pp.176-190
• /
• 2002

차량이 증가함에 따라 전방의 상황을 운전자에게 알려주기 위한 운전자 도움 시스템(Advanced Drivers Assistance System)과 같은 체계가 요구된다. 본 논문에서는 전방의 상황을 운전자에게 알려 주기 위한 기본과정으로 연속된 컬러 영상으로부터 영상처리만을 이용하여 전방의 차량과 차선을 검출하는 방법을 제안한다. 도로 전방의 상황은 차량이 많다고 하더라도 도로의 영역이 많은 부분을 차지하고 있으며, 차량이 있는 경우에 차량의 하단에 그림자와 같이 어두운 영역이 존재하는 점을 이용하여 전방의 차량을 검출한다. 그리고 차선은 그림자 영역의 반대 특징으로 횐색계열이라는 점을 이용하여 차선 정보를 추출한다. 이 방법은 도로가 혼잡하거나 도로상에 방향 표시가 있는 경우에도 좋은 결과를 보인다. 차량과 차선을 검출하는데는 HSV 컬러 모델에서 태도 성분과 명도 성분을 이용하여 후보점을 검출하고, 차량과 타선의 영역을 검출하며 에지 정보를 이용하여 차량의 영역을 결정한다. 그리고 검출된 차량 영역이 이전 프레임의 차량 영역과 같은 차량인지 알기 위해서는 HSV 성분과 위치 정보의 통계적 특징을 이용한다. 제안된 방식의 효과를 검증하기 위해 노트북 PC와 PC용 CCD 카메라로 도로에서의 영상을 촬영하고 차량 및 차선 검출 알고리즘을 적용한 처리 시간, 정확도 및 차량검지 결과를 보인다.

• 한국인쇄학회:학술대회논문집
• /
• 한국인쇄학회 2000년도 춘계 학술발표회 논문집
• /
• pp.25-34
• /
• 2000

Recently, color proofing in printing industry grow rapidly. If an order decide color from known color information in the case of color reproduction, we can reduce expenses and time. In color proofing the best important point must be closed proofed color to primary color and secondary color. Model-based approaches have the advantages of faster recharacterization and the opportunity of simulating product enhancements such as changes in ink properties and halftoning. In this paper, we transformed the dot area of CMYK to CIELAB color space using color reprodution models. Firstly, we measured spectral reflectance of primary color printed by Matchprint II and the data was used to find tone reproduction curve using regression equation, and than we applied at primary color model, such as Murray-Davies, Yule-Nilsen, and mixed color model, such as Kubelka--Munk, relaxed version of spectral Neugebauser. In such results, the Kubleka-Munk model resulted in the best spectral reconstruction accuracy followed by relaxed version of spectral Neugebauer model, color difference is 2.8401.

• 대한치과보철학회지
• /
• 제42권4호
• /
• pp.443-457
• /
• 2004

Purpose: The purpose of this study was to analyze and estimate whether each company may produce the color of artificial teeth as it stands, in the standard of vita classical shade guide using ShadeScan$^{TM}$ System. Material and methods: we chose the products of 6 companies -EFUCERA, IVOCLAR, ENDURA, TRUBYTE, DURADENT, and DURACROSS- estimated the shade value of each fixed point(cervical, body, and incisal area) of artificial tooth, and verified the equality among the samples from the same company. Results: First, the variation appeared significant at cervical and incisal area. It means that there were significant differences between cervical and incisal area although the most similar artificial teeth to the patients’natural teeth were provided. Second, the results in the body area showed that the variation between artificial and natural teeth was finite(p<0.05) in that area. Conclusion: it shows that the reproduction of colors of artificial teeth might be successful regarding the body is the most important part for a determination of the color of artificial teeth. However, more complements are necessary for the better reproduction of the color of artificial teeth between cervical and incisal area.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.111.1-111
• /
• 2002

System configuration 1. First is the image acquisition part 2. Second part is for creating the vector image and for processing the obtained facial image. This part is for finding the facial area from the skin color. To do this, we can first find the skin color area with the highest weight from eigenface that consists of eigenvector. And then, we can create the vector image of eigenface from the obtained facial area. 3. Third is recognition module portion.

• 복식
• /
• 제52권8호
• /
• pp.29-39
• /
• 2002

It was increased leisure hours by automation and computerization of industry. Many people spend on hours in enjoying leisure sports, and then. nowadays, Many women tend to prefer casual wear to formal suits. The purpose of this research was to design of outdoor-wear that improve the functional and aesthetic effects for clothing comfort. Total 4 design prototype consisting of jumper and slacks were developed for this research. Outdoor-wear design forced on armhole type of jumper and ease of the back crotch length of slacks to improve the functional and aesthetic effects. And Outdoor-wear design focused on color harmony to aesthetic effects. Ease amount and materials of jumper and slacks were controlled. Design A: Jumper was designed as dropped shoulder with set-in steeve and band collar, A break-away zipper to facilitate ventilation control were made the area of back of jumper and the area of outside seam line of slacks Color of jumper and slacks were olive green color. Ease amount of the crotch length of slacks pattern was constructed as 7% of total crotch length: Design B 4DM cut pattern were applied to the jumper and slacks pattern. A break-away zipper to facilitate ventilation control were made the area of back of jumper and the area of inside seam line of thigh. Color of jumper and slacks were grey and orange color. Ease amount of the crotch length of slacks pattern was constructed as 5% of total crotch length. Design C : Jumper was designed as the set in sleeve and hood. and A break- away zipper to facilitate ventilation control were made the ares of the armhole and elbow. Color of jumper and slacks were ivory and orange color. Ease amount of the crotch length of slacks pattern was constructed as 5% of total crotch length. Design D : Jumper was designed as raglan sleeve. Color of jumper and slacks were olive green color. Ease amount of the crotch length of slacks pattern was constructed as 5% of total crotch length. Total six females, ages 20-45, served as subjects for this research. Subjects have standard body type, generally, wearing 66 size of ready-to-wear clothing. The performance of the newly designed outdoor-wear was evaluated for their effectiveness in several aspects such as conditions of skin temperature, sensory evaluation of comfort during body movements, appearance and color harmony and aesthetic collar design. Design 3 was appeared to be the most positive in aesthetic evaluation and functional effects of design 2 of 4DM cut pattern was appeared to be beter than other designs.

• 한국정보통신학회논문지
• /
• 제22권3호
• /
• pp.434-442
• /
• 2018

본 논문에서는 주행하는 차량에 탑재된 카메라에서 획득한 도로 영상에서 차선의 색상을 판별하는 방법을 제안하였다. 자동차의 자율주행기술에 있어 차선 정보는 차선이탈방지(ldws), 능동적 차선유지(lkas), 고속도로주행보조(hda) 등의 자율주행의 레벨(level)이 올라갈수록 중요하다. 특히 차선의 색상, 특히 흰색 및 황색 차선의 구별은 교통사고와 직접적인 관련이 있는 정보이기에 더욱 필요한 기술이다. 본 논문에서는 주행 차선 검출 결과를 기반으로 차선 및 도로의 관심 영역을 추출하고 각 영역의 컬러 정보를 2차원 S-색상 공간으로 투영하였다. S-공간에 투영된 색상의 특징 분포에서 개선된 mean-shift 알고리즘을 이용하여 특징의 무게중심을 구하였다. 좌, 우 차선과 도로영역의 색상특징의 중심점들 사이의 거리 정보를 이용하여 차선의 색상을 판별하였다. 다양한 조명환경에서 약 97%의 색상 인식 성공률을 보였다.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.197-197
• /
• 2017

In order to reduce the loss of perilla seeds at harvesting stage, different seeding methods and harvesting time had been applied to upland soil in NICS (National Institute of Crop Science), RDA, Milyang, Korea. The seeding methods were divided into hill and drill seeding, and harvesting time were 40%, 60%, 80%, and 100% color-changing of top cluster perilla (cv Deulsaem) seeds. Higher plant height and lowest flower cluster, thinner culm thickness was observed in drill seeding treated plot than hill seeding treated plot. However, field lodging occurred lower at drill seeding treatment (lodging degree 3) than hill seeding plot (lodging degree 5). Harvesting time affected the loss of perilla seeds and the loss rate of perilla seeds were investigated at different color-changing of top flower cluster. When seeds were harvested at 40%, 60%, 80%, and 100% color-changing of top cluster perilla seeds, the loss rate of hill and drill seeding showed no significant differences however the loss rated of 40, 60, 80, and 100 % color-changing of top flower cluster were 1.9% to 3.0%, 3.8% to 3.9%, 8.0% to 10.2%, and 16.1% to 22.7%, respectively. The harvesting time had no significant effects on the yield of perilla seeds. These results suggest that optimum harvesting time of perilla could be recommend at the 60% color-changing of top cluster to reduce the loss of perilla seeds.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.63-65
• /
• 2005

In this study, the automatic face tracking algorithm is proposed by using the color and edge information of a color image. To reduce the effects of variations in the illumination conditions, an acquired CCD color image is first transformed into YCbCr color coordinates, and subsequently the morphological image processing operations, and the elliptical geometric measures are applied to extract the refined facial area.

• 한국항행학회논문지
• /
• 제15권6호
• /
• pp.1132-1137
• /
• 2011

본 논문에서는 사람의 신체 일부분을 추적하는 시스템을 위해서 피부영역을 추출하고 여러 개의 영역을 추적하는 다중 CAMShift 알고리즘(Multi Continuously Adaptive Mean Shift Algorithm)을 제안하였다. 입력 영상에서 피부영역을 추출하기 위해 영상의 RGB의 특정값을 기준으로 피부색에 적응적인 임계값을 적용하였다. 이때 적용된 피부영역을 양손, 얼굴 등에 초기 윈도우를 설정하였다. 이 영역들을 추적함에 있어 영역들 사이에 폐색 영역을 회피하기 위해 가우시안 배경 모델(Gaussian Background Model)을 사용하여 각 추적 영역들을 제한하였다. 또한 폐색영역에 가중치를 부가하여 확률분포영상에서 중심값을 이동시켜 폐색 영역을 회피하였다. 실험 결과 다중 물체들에 강인한 추적을 보이고 유사한 색상을 갖는 물체의 폐색 시에도 우수한 결과를 보임을 확인하였다.