• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2005년도 하계학술대회 논문집 Vol.6
• /
• pp.72-73
• /
• 2005

In this paper, the simulation of the n-p-n-p layer stacked color detector is presented. A color detector based on vertically integrated structures of silicon can overcome color moire or color aliasing effect. The color detector is designed to separate the fundamental chromatic components at each junction and exhibits maxima of the spectral sensitivity at red, green, and blue region, respectively. From this result, it is observed that the spectral response can be controlled by the doping concentration and structure of the devices.

• 한국전기전자재료학회논문지
• /
• 제15권7호
• /
• pp.583-590
• /
• 2002

In this paper, a new Silicon on Insulator (SOI)-based photodetector was proposed, and its basic operation principle was explained. Fabrication steps of the detector are compatible with those of conventional SOI CMOS technology. With the proposed structure, RGB (Read, Green, Blue) which are three primary colors of light can be realized without using any organic color filters. It was shown that the characteristics of the SOI-based detector are better than those of bulk-based detector. To see the response characteristics to the green (G) among RGB, SOI and bulk NMOSFETS were fabricated using $1.5\mu m$ CMOS technology and characterized. We obtained optimum optical response characteristics at $V_{GS}=0.35 V$ in NMOSFET with threshold voltage of 0.72 V. Drain bias should be less than about 1.5 V to avoid any problem from floating body effect, since the body of the SOI NMOSFET was floated. The SOI and the bulk NMOSFETS shown maximum drain currents at the wavelengths of incident light around 550 nm and 750 nm, respectively. Therefore the SOI detector is more suitable for the G color detector.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.1093-1096
• /
• 1999

In this paper, video image segmentation algorithm based on color histogram and change detector is proposed. Color histograms are calculated from both changed region which is detected in the previous and current frame and unchanged region. With each histogram, modes and valleys are detected. Then, color vectors are calculated by averaging pixels in modes. Markers are extracted by labeling color vectors that represent modes, the watershed algorithm is applied to determine uncertain region. In growing region, the root mean square(RMS) of the distance between average pixel in marker region and adjacent pixel is used as a measure. The proposed algorithm based on color histogram and change detector segments video image fastly and effectively. And simulation results show that the proposed method determines the exact boundary between background and foreground.

• 한국통신학회논문지
• /
• 제22권7호
• /
• pp.1566-1573
• /
• 1997

In this paper, we propose a favorite color correction algorithm for color enhancement in color application system which represent preferred colors for viewer's demands. The proposed algorithm corrects skin color which is widely used as a reference color for color control of color application system, blue color which is directly related to tri-stimulus values, and green color which has higher visual sensitivity. In the proposed algorithm, the vaiation range of phase detector output voltage was minimized for the favorite color saturation changes, thus the favorite from the burst signal for the phase detector characteristic, thus the favorite color was easilty detected from the other color without overlapping of correctionranges.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1993년도 Proceedings of International Conference for Agricultural Machinery and Process Engineering
• /
• pp.353-362
• /
• 1993

The purpose of this study is to develop a crop-row detector which can be applied to an automatic row following control for cultivators or thinning machines. In this report, a possibility of new crop-row detecting method was discussed. This detecting method consists of two principal means. One is the hardware means to convert the two dimensional crop-row vision to the compacted one dimensional information. The conversion is achieved by a color line sensor and a rotating mirror. In order to extract crop-row , R and G signals of RGB color system are used. The locations of two different points on the target row are detected by this means. Another is the software means to estimate the offset value and the heading angle between the detector and the target row which can be assumed as a straight line. As a result of discussion, it was concluded that this detecting method would be accurate enough for practical use.

• 제어로봇시스템학회논문지
• /
• 제22권3호
• /
• pp.241-246
• /
• 2016

Nowadays many people have an interest in facial expression and the behavior of people. These are human-robot interaction (HRI) researchers utilize digital image processing, pattern recognition and machine learning for their studies. Facial feature point detector algorithms are very important for face recognition, gaze tracking, expression, and emotion recognition. In this paper, a cascade facial feature point detector is used for finding facial feature points such as the eyes, nose and mouth. However, the detector has difficulty extracting the feature points from several images, because images have different conditions such as size, color, brightness, etc. Therefore, in this paper, we propose an algorithm using a modified cascade facial feature point detector using a convolutional neural network. The structure of the convolution neural network is based on LeNet-5 of Yann LeCun. For input data of the convolutional neural network, outputs from a cascade facial feature point detector that have color and gray images were used. The images were resized to $32{\times}32$. In addition, the gray images were made into the YUV format. The gray and color images are the basis for the convolution neural network. Then, we classified about 1,200 testing images that show subjects. This research found that the proposed method is more accurate than a cascade facial feature point detector, because the algorithm provides modified results from the cascade facial feature point detector.

• 한국정보통신학회논문지
• /
• 제14권2호
• /
• pp.375-382
• /
• 2010

본 논문은 피사체의 고유의 색을 나타내기 위한 자동 백색 보정 기능에서 단색 영상에 대한 색상 왜곡현상을 보정하는 단색 영상 검출기의 구조개선 및 성능 향상을 수행한 구조를 제안한다. 제안한 구조는 뛰어난 효율성으로 인해 모바일 폰 카메라에 널리 사용되는 Grayworld 알고리듬을 통한 백색 보정 기능에 적용되는 단색 영상 검출기로써, 입력 영상의 색 분포 특성을 파악하여 단색 영상의 입력 시 해당 색상을 제외한 나머지 영역으로 자동 백색 보정기능을 수행하도록 하는 역할을 수행한다. 제안한 구조는 기존 구조에 비해 다양한 영상의 입력에 대응 가능하며, 영상의 크기 및 촬영 환경에 따라 임계값의 변경이 가능하도록 설계하였다. 또한 하드웨어 구조의 간소화를 통해 기존 대비 약 80%의 하드웨어 크기가 감소되었다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권7호
• /
• pp.548-559
• /
• 2009

Viola와 Jones가 제안한 에이다부스트 얼굴 검출기는 속도와 정확도면에서 매우 훌륭한 성능을 보이고 있는 얼굴 검출기이다. 하지만 에이다부스트 얼굴 검출기에도 여전히 오검출이 발생하며, 이를 줄이기 위해서는 더욱 많은 계산이 필요하다. 에이다부스트 얼굴 검출기는 흑백 영상만을 사용하므로, 색상정보를 사용하면 더 적은 연산으로 오검출율을 낮출 수 있다. 본 논문은 얼굴 색상 정보를 이용하여 대상 영상에서 부 윈도우를 효율적으로 검색하고, 에이다부스트 얼굴 검출기의 첫 단계에 계산속도가 매우 빠른 얼굴 색상을 이용한 얼굴/비얼굴 분류기를 채용하여 더 빠른 얼굴 검출 속도와 더 낮은 오검출율을 달성할 수 있는 단계별 얼굴 검출 모텔을 제안하였다. 얼굴색상 필터링을 위해 정의된 얼굴색상 소속함수를 이용하여 얼굴색상 필터 영상과 그 누적영상을 계산한다. 누적 영상에 의해 빠른 속도로 임의의 부 윈도우의 밀도를 계산할 수 있다. 제안된 검색 방법은 이 색상 밀도에 기반하여 얼굴일 가능성이 없는 부 윈도우들을 생략하게 된다. 그리고 부 윈도우의 밀도를 이용한 얼굴/비얼굴 분류기는 단계별 얼굴 검출기의 앞단에서 얼굴이 아닌 부 윈도우를 빠르게 거절한다. 제안된 얼굴 검출 모델은 적은 계산으로 오검출율을 낮출 수 있었으며, 실시간 얼굴 검출 속도를 비약적으로 향상시킬 수 있었다.

• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.239-245
• /
• 2004

본 논문에서는 그림자가 존재하는 환경 하에서도 실제 코너만을 정확하게 추출할 수 있는 색상 기반 내잡음성 코너 검출자를 제안하였다. 먼저 그림자 경계에서 명도의 변화는 크지만 색상의 변화는 크지 않으므로 각 화소에 대한 HSI 색 공간에서 색상 가중 조합 벡터 기울기를 코너 검출자에 반영함으로써 그림자의 영향을 제거하고, 선택된 에지 화소 쌍의 색 변화 방향이 서로 반대 극성일 때는 코너 기여 가중치를 상쇄시킴으로써 불규칙 잡음에도 강건하게 코너를 검출하도록 하였다. 실험을 통하여 제안한 코너 검출자가 그림자 및 불규칙 잡음에도 강건하게 실제 코너만을 효과적으로 검출함을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1956-1960
• /
• 1991

This paper describes the measured results upon monochromatic light, compound light, and light emanated from light emitting diodes by a simplified wavemeter with a semiconductor color sensor. Since a single unit element of a semiconductor color sensor with two PN junction photodiodes has been developed, the author has fabricated the simplified wave detector by using the element. The simplified wive detector has been measured results upon monochromatic light, compound light, and light emanated from light emitting diodes. Since luminescent color of each diode locates in luminosity region, comparison of measured values of PD-150 and PD-151 resulted no remarkable difference in averaged wave length. As for monochromatic light, PD-151 showed very cross value to the color filter peak value rather than PD-150. As for compound light, PD-150 has shown such influence of long wave length light which reaches to near infrared ray with respect to PD-151.