• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(3)
• /
• pp.141-144
• /
• 2001

In this paper, a new algorithm for extracting and recognizing characters from video, without pre-knowledge such as font, color, size of character, is proposed. To improve the recognition rate for videos with complex background at low resolution, continuous frames with identical text region are automatically detected to compose an average frame. Using boundary pixels of a text region as seeds, we apply region filling to remove background from the character Then color clustering is applied to remove remaining backgrounds according to the verification of region filling process. Features such as white run and zero-one transition from the center, are extracted from unknown characters. These feature are compared with a pre-composed character feature set to recognize the characters.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1291-1294
• /
• 2003

This paper presents an approach to extract license plates from parking regulation images which is captured in various photographing direction and complex background. first, we search each row at regular intervals starting from the bottom of a license-plate image, and we set up a rough region for a certain zone in which the sign of intensity vector changes frequently enough and color of license plate is detected enough, assuming it as a candidate location of a license plate. And then, we extract an elaborate area of a license plate by horizontally and vertically projecting vertical edges. Here, tar types of the private and the public, are easily classified according to the color of extracted plates. To evaluate proposed method, we used 200 actual regulation images. As a result, the proposed method showed extraction rate of 96%, which is 9% higher than the previous method using only intensity vector.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.251-252
• /
• 2007

The thesis proposed the Text Extraction Algorithm which is a text extraction algorithm which uses the Coiflet Wavelet, YCbCr Color model and the close curve edge feature of adaptive LoG Operator in order to complement the demerit of the existing research which is weak in complexity of background, variety of light and disordered line and similarity of text and background color. This thesis is simulated with natural images which include naturally text area regardless of size, resolution and slant and so on of image. And the proposed algorithm is confirmed to an excellent by compared with an existing extraction algorithm in same image.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.159-168
• /
• 2019

Accurate forest fires detection algorithms remain a challenging issue, because, some of the objects have the same features with fire, which may result in high false alarms rate. This paper presents a new video-based, image processing forest fires detection method, which consists of four stages. First, a background-subtraction algorithm is applied to detect moving regions. Secondly, candidate fire regions are determined using CIE $L{\ast}a{\ast}b{\ast}$ color space. Thirdly, special wavelet analysis is used to differentiate between actual fire and fire-like objects, because candidate regions may contain moving fire-like objects. Finally, support vector machine is used to classify the region of interest to either real fire or non-fire. The final experimental results verify that the proposed method effectively identifies the forest fires.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.166-179
• /
• 2021

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

• 조명전기설비학회논문지
• /
• 제29권1호
• /
• pp.22-30
• /
• 2015

Currently, in South Korea, 'Light Pollution Prevention Act by Artificial Lighting' has been enforced. For advertising lighting, it is limited based on only the light-emitting luminance. Luminance is a concept related to the glare. Not only the luminance of the light source, but also glare is affected depending on some situations like blinking, luminance contrast, background illuminance. This study conducted glare subjective evaluation with brightness, color, and blinking by looking at the LED lighting box. The results showed that the glare indexes were higher about 2 times in a decrease of background illuminance from 100lx to 0lx. The glare index of R, G, B light was higher than that of white light. The average glare index of the blue light was higher about 8 times compared to 2,700K. And the blink rate had little effect on the glare, but it affected the irritation. Therefore, the glare effect of light color and blinking needs to be considered for the standard of luminous environment.

• 한국임상약학회지
• /
• 제23권2호
• /
• pp.97-105
• /
• 2013

Background: This study was aimed to establish the systematic management methods of tar color additives used in Korea for drugs and quasi-drugs. Although tar color additives have been used in various areas, safety problems are continuously being reported by several studies. For that reason, major countries like US, Japan, Europe are trying to update the safety information of tar color additives and the related management methods, and Korea also need to complement them based on the updated information for their safer use. Method: This report includes the compared information of all legally used tar color additives of each country, such as color additive name, compound name and chemical abstracts service registry number. Conclusion: It is expected that these investigated results will be useful as the basic materials for proper management guidelines of tar color additives in Korea.

• 한국의상디자인학회지
• /
• 제17권2호
• /
• pp.207-222
• /
• 2015

The purpose of this study is to set up the theoretical foundation for neon colors by recognizing them as important elements of sensitive design and by comprehending their existence as a color fashion responsive to psychological and social background. As the subject of the present the researcher has selected important oversea collections of these five years during which neon colors have fully emerged as popular colors of fashion. The procedure of research was to examine the concept and traits of colors and investigate the utility of neon colors in various fields. The important facts which are acquired from the present study are as follows. First, the analysis of frequency has found out the following color arrangements: neon color only-8.6%(35), neon color+colorless-58.3%(236), neon color+ colored -14.8%(60),neon color+colorless+colored-18.3%(74), and others. The case of neon color used as monochromatic (color) was distinguished into two: single neon color all through and the same color used differently. Color arrangements were divided into analogous arrangement, separation arrangement, dominant arrangement, multi-color arrangement, and accent arrangement. Second, the internal significance of neon colors expressed in fashion can be interpreted into three: emphasis, optical Illusion, and amusing. This study has attempted to raised up the aesthetic value of various color expression and to expand fashion image by interpreting the trends of color fashion together with the traits and aesthetic meaning of color in fashion. The future study intends to expand the expression area of fashion design and to interpret molding beauty through the image of color arrangement and through fashion style utilizing neon colors.

• 한국콘텐츠학회논문지
• /
• 제5권4호
• /
• pp.85-93
• /
• 2005

본 논문은 복잡한 배경에서 표식없는 손을 추적하여 한글 수화를 인식하는 시스템에 관한 것이다. 제안한 방법은 먼저 인접한 프레임간의 차 영상에 대하여 엔트로피를 측정한다. 큰 값을 갖는 영역에 대해 피부색에 가까운 분포를 갖는 색상 정보를 추출하여 배경 영상으로부터 손 영역만을 추출한다. 추출된 손 영역에 대해 윤곽선을 검출하고 개선된 무게중심 프로필(centroidal profile) 방법을 적용하여 수화를 인식한다. 6가지 모양의 수화를 사용한 실험결과 기존의 방법들과 달리 표식을 사용하지 않고도 복잡한 배경과 조명의 변화에서 안정적으로 수화를 인식할 수 있다. 또한 초당 15프레임 정도의 처리속도로 각 사람별로 95%이상, 각 수화별로 $90\sim100%$의 인식률을 얻을 수 있다.

• 정보처리학회논문지B
• /
• 제10B권4호
• /
• pp.473-478
• /
• 2003

본 논문은 복잡한 영상에서 추출해낸 손 영역으로부터 움직임 정보를 이용하여 제스처를 인식하는 시스템에 관한 것이다. 제안한 방법은 먼저 인접한 프레임간의 파 영상에 대하여 엔트로피를 측정한다. 큰 값을 갖는 영역에 대해 피부색에 가까운 분포를 갖는 색깔 정보를 추출하여 배경 영상으로부터 손 영역만을 추출한다. 추출된 손 영역에 대해 체인코드를 이용하여 외곽선을 검출하고 개선된 무게중심 프로필(centroidal profile) 방법을 적용하여 손의 제스처론 인식한다. 6가지 모양의 손 제스처를 사용한 실험 결과 기존의 방법들과 달리 표식을 사용하지 않고도 복잡한 배경과 조명의 변화에서 안정적으로 손 제스처를 인식할 수 있다. 또한 초당 15프레임 정도의 처리속도로 각 사람별로 95% 이상, 각 제스처별로 99∼100%의 인식률을 얻을 수 있다.