• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.715-721
• /
• 2000

In this research, rule and neuro net based boundary extraction algorithm was developed. Extracting boundary of the interest, lean tissue, is essential for the quality evaluation of the beef based on color machine vision. Major quality features of the beef are size, marveling state of the lean tissue, color of the fat, and thickness of back fat. To evaluate the beef quality, extracting of loin parts from the sectional image of beef rib is crucial and the first step. Since its boundary is not clear and very difficult to trace, neural network model was developed to isolate loin parts from the entire image input. At the stage of training network, normalized color image data was used. Model reference of boundary was determined by binary feature extraction algorithm using R(red) channel. And 100 sub-images(selected from maximum extended boundary rectangle 11${\times}$11 masks) were used as training data set. Each mask has information on the curvature of boundary. The basic rule in boundary extraction is the adaptation of the known curvature of the boundary. The structured model reference and neural net based boundary extraction algorithm was developed and implemented to the beef image and results were analyzed.

• 한국정보통신학회논문지
• /
• 제17권12호
• /
• pp.2927-2936
• /
• 2013

본 논문에서는 3D 콘텐츠 생성 시 필요한 깊이 영상의 화질 개선을 위하여 잡음 제거 기법과 홀 채움 기법을 제안한다. 제안하는 기법에서는 컬러 영상과 깊이 영상을 모두 이용하게 된다. 먼저 입력된 컬러 영상을 RGB 색상계에서 HSI 색상계로 변환하여 밝기 영상을 생성한다. 그리고 깊이 영상에서 기준 화소와 주변 화소간의 거리 값, 깊이 값의 차이를 구하고 컬러 영상의 밝기 값 차이를 계산하여 제안하는 잡음 제거 기법에 이용한다. 이후 홀을 탐색하여 홀과 주변 화소간의 거리, 컬러 영상의 밝기 값 차이를 제안하는 홀 채움 기법을 적용하여 깊이 영상 내에 존재하는 홀을 채우게 된다. 마지막으로 실시간 환경에 적용하기 위하여 제안하는 기법을 GPU로 병렬화하여 속도 향상을 하고자 하였다. 실험을 통하여 제안한 기법이 기존 기법에서 발생하는 경계 부분의 흐려짐 현상을 줄이면서 홀을 채우는 것을 확인하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권6호
• /
• pp.383-389
• /
• 2016

This paper presents a novel automatic white balance (AWB) algorithm for consumer imaging devices. While existing AWB methods require reference white patches to correct color, the proposed method performs the AWB function using only an input image in two steps: i) white point detection, and ii) color constancy gain computation. Based on the dark channel prior assumption, a white point or region can be accurately extracted, because the intensity of a sufficiently bright achromatic region is higher than that of other regions in all color channels. In order to finally correct the color, the proposed method computes color constancy gain values based on the Y component in the XYZ color space. Experimental results show that the proposed method gives better color-corrected images than recent existing methods. Moreover, the proposed method is suitable for real-time implementation, since it does not need a frame memory for iterative optimization. As a result, it can be applied to various consumer imaging devices, including mobile phone cameras, compact digital cameras, and computational cameras with coded color.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권1호
• /
• pp.1-12
• /
• 2008

본 논문에서는 야외 및 실내에서 촬영된 차량 영상에 대해 실시간으로 차량 색상을 인식할 수 있는 GPU(Graphics Processing Unit) 기반의 알고리즘을 제시한다. 전처리 과정에서는 차량 색상의 표본 영상들로부터 특징벡터를 계산한 뒤, 이들을 색상 별로 조합하여 GPU에서 사용할 참조 텍스쳐(Reference texture)로 저장한다. 차량 영상이 입력되면, 특징벡터를 계산한 뒤 GPU로 전송하고, GPU에서는 참조 텍스쳐 내의 표본 특징리터들과 비교하여 색상 별 유사도를 측정한 뒤 CPU로 전송하여 해당 색상명을 인식한다. 분류의 대상이 되는 색상은 가장 흔히 발견되는 차량 색상들 중에서 선택한 7가지 색상이며, 검정색, 은색, 흰색과 같은 3가지의 무채색과 빨강색, 노랑색, 파랑색, 녹색과 같은 4가지의 유채색으로 구성된다. 차량 영상에 대한 특징벡터는 차량 영상에 대해 HSI(Hue-Saturation-Intensity) 색상모델을 적용하여 색조-채도 조합과 색조-명도 조합으로 색상 히스토램을 구성하고, 이 중의 채도 값에 가중치를 부여함으로써 구성한다. 본 논문에서 제시하는 알고리즘은 다양한 환경에서 촬영된 많은 수의 표본 특징벡터를 사용하고, 색상 별 특성을 뚜렷이 반영하는 특징벡터를 구성하였으며, 적합한 유사도 측정함수(likelihood function)를 적용함으로써, 94.67%에 이르는 색상 인식 성공률을 보였다. 또한, GPU를 이용함으로써 대량의 표본 특징벡터의 집합과 입력 영상에 대한 특징벡터 간의 유사도 측정 및 색상 인식과정을 병렬로 처리하였다. 실험에서는, 색상 별로 1,024장씩, 총 7,168장의 차량 표본 영상을 이용하여 GPU에서 사용하는 참조 텍스쳐를 구성하였다. 특징벡터의 구성에 소요되는 시간은 입력 영상의 크기에 따라 다르지만, 해상도 $150{\times}113$의 입력 영상에 대해 측정한 결과 평균 0.509ms가 소요된다. 계산된 특징벡터를 이용하여 색상 인식의 수행시간을 계산한 결과 평균 2.316ms의 시간이 소요되었고, 이는 같은 알고리즘을 CPU 상에서 수행한 결과에 비해 5.47배 빠른 속도이다. 본 연구에서는 차량만을 대상으로 하여 색상 인식을 실험하였으나, 일반적인 피사체의 색상 인식에 대해서도 제시된 알고리즘을 확장하여 적용할 수 있다.

• 한국멀티미디어학회:학술대회논문집
• /
• 한국멀티미디어학회 2002년도 춘계학술발표논문집(상)
• /
• pp.295-298
• /
• 2002

본 논문에서는 한 장의 칼라 영상을 형성시키는 광원의 색온도를 추정하는 새로운 방법을 제안한다. 주어진 한 장의 칼라 영상으로부터 광원의 색도 좌표를 계산하는데 필요한 R,G,B 값이 특정한 칼라에 편향되지 않는 기준 백색 영역을 추출한다. 추출된 기준 백색 영역 내에서 계산된 (x,y) 색도 좌표로부터 등 색온도선을 이용하여 최종적으로 주어진 칼라 영상을 형성시키는 광원의 색온도를 추정한다. 캐나다 Simon Fraser 대학에서 제공되는 205장의 영상을 이용하여 제안된 방법과 기존 방법들을 비교 실험한 결과로부터 제안된 방법으로 추정한 색온도가 상대적으로 작은 오차를 나타냄을 확인하였다.

• 한국실내디자인학회논문집
• /
• 제22권1호
• /
• pp.247-255
• /
• 2013

In this study, the colors and characteristics of Gwangbok-ro of Busan were analyzed in the standpoint of local images based on the examination of the facade designs of stores along the road of Gwangbok-ro, Busan a main street with massive population flow. To that end, the facades of stores, correlation with the city, color and locality were examined, and after the status of facade designs in Gwangbok-ro were identified through case survey by it, color images were analyzed. For color analysis, Munsell color system was used as basic tool. As a result of examining the colors in Gwangbok-ro area, the following status could be analyzed on 3 attributes of hue, brightness and chroma: First, analysis results of hue indicated that dominant color that covers 70% or more of the area represented mid brightness and low chroma in GY(36.1%) series, subsidiary color which covers 25% or more of the area mid brightness and low chroma in YR(26.5%) series, and accent color that covers less than 5% of the area high brightness and low chroma of GY(40%) series. Second, in brightness analysis, dominant color mostly represented mid brightness, subsidiary color mid brightness and accent color high brightness respectively. In particular accent color showed more intensive crowding phenomenon in high brightness. Third, as for chroma, dominant color, subsidiary color and accent color all are gathered in low chroma, however in small number of accent colors, peculiar high chroma appeared notable. In conclusion, the colors of Gwangbok-ro area analyzed based on the facade design of the stores along the road in this study were superficial colors that reflect the life of people in the area, artificial colors by improvement of the local environment. This study is meaningful in that the image of Gwangbok-ro was found through building colors in one part of the city Busan. It is judged that the study results would become useful as reference document in planning out environment colors later on.

• The Journal of Advanced Prosthodontics
• /
• 제10권3호
• /
• pp.218-226
• /
• 2018

PURPOSE. The aim of this study was to define a color space of non-vital teeth and to compare it with the color space of matched vital teeth, recorded in the same patients. MATERIALS AND METHODS. In a group of 218 patients, with the age range from 17 to 70, the middle third of the buccal surface of 359 devitalized teeth was measured using a clinical spectrophotometer (Vita Easyshade Advance). Lightness ($L^*$), chromatic parameters ($a^*$, $b^*$), chroma ($C^*$), hue angle (h) and the closest Vita shade in Classical and 3D Master codifications were recorded. For each patient, the same data were recorded in a vital reference tooth. The measurements were performed by the same operator with the same spectrophotometer, using a standardized protocol for color evaluation. RESULTS. The color coordinates of non-vital teeth varied as follows: lightness $L^*$: 52.83-92.93, $C^*$: 8.23-58.90, h: 51.20-101.53, $a^*$: -2.53-24.80, $b^*$: 8.10-53.43. For the reference vital teeth, the ranges of color parameters were: $L^*$: 60.90-97.16, $C^*$: 8.43-39.23, h: 75.30-101.13, $a^*$: -2.36-9.60, $b^*$: 8.36-39.23. The color differences between vital and non-vital teeth depended on tooth group, but not on patient age. CONCLUSION. Non-vital teeth had a wider color space than vital ones. Non-vital teeth were darker (decreased lightness), more saturated (increased chroma), and with an increased range of the hue interval. An increased tendency towards positive values on the $a^*$ and $b^*$ axes suggested redder and yellower non-vital teeth compared to vital ones.

• 한국멀티미디어학회논문지
• /
• 제19권3호
• /
• pp.642-649
• /
• 2016

This paper presents a method for conversion of muscular sense into both visual and auditory senses based on synesthetic perception. Muscular sense can be defined by rotation angles, direction changes and motion degrees of human body. Synesthetic interconversion can be made by learning, so that it can be possible to create intentional synesthetic phenomena. In this paper, the muscular sense was converted into both color and sound signals which comprise the great majority of synesthetic phenomena. The measurement of muscular sense was performed by using the AHRS(attitude heading reference system). Roll, yaw and pitch signals of the AHRS were converted into three basic elements of color as well as sound, respectively. The proposed method was finally applied to a wearable device, Samsung gear S, successfully.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.289-292
• /
• 2007

물체컬러식별 임베디드시스템을 프로세서 기반으로 구현하고 물체를 식별 분류하는 무인물류관리 시스템을 제한한다. 임베디드시스템 구현은 초음파 센서를 이용하여 물체의 유무와 거리를 추출하고 USB CCD 카메라로부터 이진영상을 획득한다. 영상식별 알고리듬은 입력영상에 대해 컬러 검출한 패턴을 기준패턴과 비교 식별하여 지정된 랙에 이동 저장한다. 실험결과 무인화 창고관리 로봇기능으로 실용가능성을 제시하였다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1224-1227
• /
• 2009

When evaluating the quality of images and displays, it is important to combine the characteristics as perceived by the human visual system and measured by equipment using subjective and objective methods, respectively. In the case of objective methods, the quality of a display is measured using colorimetric or radiometric devices according to existing standards covering the color temperature, gamut size, gamma characteristic, and device characterization. Meanwhile, subjective methods assess the quality of an image using the human visual system based on a comparison with a reference or counterpart using such metrics as the sharpness, noise, contrast, saturation, and color accuracy. Objective and subjective methods are usually used together in comparison, as ultimately it is observers watching images on a display. In addition to existing objective methods, a new image quality metric is also introduced as regards the JPEG compression ratio that is reflected in the relationship between the gamut size and the color fidelity in CIELAB color space.