• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.69-78
• /
• 2002

This paper addresses a method to automatically detect out a person's face from a given image that consists of a hair and face view of the person and a complex background scene. Out method involves an effective detection algorithm that exploits the spatial distribution characteristics of human skin color via an adaptive fuzzy color classifier (AFCC), The universal skin-color map is derived on the chrominance component of human skin color in Cb, Cr and their corresponding luminance. The desired fuzzy system is applied to decide the skin color regions and those that are not. We use RGB model for extracting the hair color regions because the hair regions often show low brightness and chromaticity estimation of low brightness color is not stable. After some preprocessing, we apply convex-hull to each region. Consequent face detection is made from the relationship between a face's convex-hull and a head's convex-hull. The algorithm using the convex-hull shows better performance than the algorithm using pattern method. The performance of the proposed algorithm is shown by experiment. Experimental results show that the proposed algorithm successfully and efficiently detects the faces without constrained input conditions in color images.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.100-102
• /
• 2001

대부분의 공간색인 방법들은 공간객체의 분포가 균일하지 않다는 가정 하에 만들어졌다. 이 가정은 실제의 응용분야에 일반적으로 적용된다. 반면에 균등한 공간객체의 분포를 위하여 만들어진 공간색인 방법들도 몇가지 있다. 예를 들어, 고정 격자 방식의 공간색인 방법은 균등한 공간객체에 대한 색인 방법으로 매우 좋은 성능을 보이며, 색인과정이 매우 단순하다는 장점이 있다. 본 논문에서는 비균일적인 공간객체의 분포를 균일분포로 변화한 다음 고정 격자 방식의 공간색인을 적용하는 방법을 제안한다. 이 방법에 따르면, 공간효율성이 매우 증가하고, 빈 공간이 줄어들어 드는 등 공간색인의 성능이 다른 색인방법에 비하여 매우 증가하며, 색인과정이 단순하여 지는 장점을 가지고 있다.

• Proceedings of the Korean Society of Fisheries Technology Conference
• /
• 2001.05a
• /
• pp.400-401
• /
• 2001

새조개(Fulvia mutica)는 우리 나라, 동중국해, 홍콩 일본 등에 분포하며, 수심 10∼50m의 사니질에 서식한다. 패각이 얇고, 패각내면은 분홍색을 띄고 있으며, 육질부의 발은 길고 검은 색이며, 맛이 매우 좋아 식용 패류로서의 가치가 매우 높다. 본 종은 일본의 경우 성장(Tain and Makoto, 1997; 1998), 자원량 평가(Tain and Makoto, 1997), 어획량과 개체군 구조(Tain and Makoto, 1997) 등 여러 분야에서 많은 연구가 이루어지고 있다. (중략)

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.666-671
• /
• 2008

In this paper, we propose a new method for tracking objects continously and successively based on fusion of region information, color information and motion template when multiple objects are occluded and splitted. For each frame, color template is updated and compared with the present object. The predicted region, dynamic template and color histogram are used to classify the objects. The vertical histogram of the silhouettes is analyzed to determine whether or not the foreground region contains multiple objects. The proposed method can recognize more correctly the objects to be tracked.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.182-183
• /
• 2018

Most of the photographs or images of the present age have pixels of various colors that can not be recognized by human eyes. For a specific purpose, pixel-based image processing is inevitable rather than passive investigation using the human eye in order to find areas of color similar to the target color. In this paper, we try to detect all the pixels of the same color or the same color in the image. We will also try to find pixels within the error range that are similar in color to the color we are looking for.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2004.12a
• /
• pp.60-65
• /
• 2004

최근 무선/이동 통신 기술과 GPS 기술의 발달은 휴대폰을 소지하고 이동하는 사람이나 GPS 수신기를 탑재한 차량과 같은 이동객체의 위치 정보와 관련된 서비스의 제공을 가능하게 하였다. 이러한 환경에서 연속적으로 변경되는 이동객체의 위치 정보는 데이터베이스에 빈번한 갱신 연산을 요구하게 되고, 이는 전체 시스템의 성능을 저하시키는 원인이 된다. 이러한 문제를 해결하기 위하여 R-Tree와 같은 공간색인 구조를 확장하여 갱신 효율을 높이기 위한 연구가 진행되어 왔지만, 시스템의 전체 성능은 오히려 저하되는 문제를 가져왔다. 이 논문에서는 이동객체의 질의 처리 성능뿐만 아니라 객체의 빈번한 위치 갱신을 효율적으로 처리할 수 있는 방법으로 고정 그리드와 R-Tree를 혼합한 형태의 색인 기법을 제안한다. 제안된 색인 기법은 R-Tree에서 색인의 재조직화로 인해 갱신 성능이 저하되는 문제를 해결하기 위하여 셀 기반 색인 기법인 고정 그리드를 이용하여 이동객체의 위치 정보를 저장하고, 고정 그리드에서 객체의 편중 분포로 인한 오버플로 문제를 처리하기 위하여 오버플로가 발생한 각각의 셀들을 R-Tree로 관리한다. 또한, 객체의 밀도가 낮은 셀들을 하나의 버켓으로 공유하여 관리함으로써 저장 공간을 효율적으로 활용한다. 제안된 방법을 다양한 평가 요소를 통해 실험한 결과, 기존의 R-Tree보다 뛰어난 갱신 성능을 보였으며, 질의 처리에 대해서도 성능이 향상되었음을 보였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3207-3213
• /
• 2011

Most methods of color constancy, which is the ability to determine the object color regardless of the scene illuminant, have failed to meet our expectation of their performance especially about low-illuminated scenes. Some methods with high performance need to be developed, but we must, above all else, obtain experimental images for analyzing the required circumstances or evaluating the methods. Therefore, the paper produces new sets of images so that they can be used in the development of color constancy methods suitable for low-illuminated scenes. These sets are composed of two parts: one part of images which are synthesized with spectral power distribution(SPD) of illuminants, spectral reflectance curve of reflectances, and sensor response functions of camera; the other part of images where the intensity of each image is adjusted at the uniform rate. In an experiment, the use of the sets takes an advantage that its result images are analyzed and evaluated quantitatively as their ground truth data are known in advance.

• Korean Journal of Optics and Photonics
• /
• v.32 no.5
• /
• pp.220-229
• /
• 2021

The optical characteristics of high-power direct-lit white light-emitting diode (LED) lighting were investigated, where a quantum dot (QD) film was adopted to enhance the color-rendering index (CRI). The transmittance of the diffuser plate and the concentration of the QD film were varied in this study. The color coordinates and the correlated color temperature (CCT) did not show any appreciable change, while the CRI values increased slightly as the transmittance of the diffuser plate decreased. The investigated optical properties were nearly independent of the viewing angle, and the luminance distribution was close to Lambertian. The CCT decreased from approximately 6000 K to approximately 4000 K as the concentration of the QD film increased from 0 to 7.5 wt%, which was due to the enhanced red component in the emission spectrum. The CRI increased to approximately 95 for some optical configurations of the lighting. These results demonstrate that glare-free, color-changeable, high-rendering LED lighting can be realized by using a combination of a diffuser plate of appropriate transmittance and a red QD film.

• Korean Journal of Plant Resources
• /
• v.16 no.3
• /
• pp.251-256
• /
• 2003

Genetic variation in field grown Korean ginseng(Panax ginseng C.A.Meyer) was evaluated using random amplified polymorphic(RAPD) markers. (This experiment was carried to collect the local native from farm of Chungnam National University in Korea in order to investigate genetic variation.) Some morphological characters showed considerable variation ranging 22 to 68cm in plant hight, 10 to 38mm in root diameter, 16 to 86g in root weight, and culum color and flowering date, respectively. Ten RAPD primers out of the 32 which produced reproducible bands in 662 Korean ginseng plants were selected for the further study. The total number of bands generated by 10 primers were 108 and among them 103 were polymorphic among the 662 plants with the polymorphism ratio of 94.5％. A total of 662 plants were classified into 16 groups based on polymorphic data with an URP 05 primer.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.3
• /
• pp.292-303
• /
• 2001

Object color can be determined by the characteristic of scene illuminant and surface. In this paper, perceived illumination effect is extended and with the highlight analysis, hybrid approach is proposed to estimate the illuminant chromaticity. The perceived illumination approach provides a stable candidate range for the estimation of illuminant chromaticity, however, the accuracy is slightly degraded depending on the image contents. The highlight approach does not depend on the image contents and provides an accurate solution of the scene illuminant chromaticity, however, it is difficult to determine the final solution among many cross-points. These two approaches are in effect mutually compensating. The solution from perceived illumination can be used as a starting point or as base information for the highlight approach to get the final solution.