• 한국군사과학기술학회지
• /
• 제23권2호
• /
• pp.139-146
• /
• 2020

The camouflage pattern was difficult to distinguish from the surrounding background, so it was difficult to classify the object and the background image when the color image is used as the training data of deep-learning. In this paper, we proposed a red-green color blindness image transformation method using the principle that people of red-green blindness distinguish green color better than ordinary people. Experimental results show that the camouflage soldier's recognition performance improved by proposed a deep learning model of the ensemble technique using the imitated red-green-blind image data and the original color image data.

• 한국멀티미디어학회논문지
• /
• 제15권4호
• /
• pp.449-471
• /
• 2012

In intelligent surveillance systems, it is required to robustly track multiple people. Most of the previous studies adopted a Gaussian mixture model (GMM) for discriminating the object from the background. However, it has a weakness that its performance is affected by illumination variations and shadow regions can be merged with the object. And when two foreground objects overlap, the GMM method cannot correctly discriminate the occluded regions. To overcome these problems, we propose a new method of tracking and identifying multiple people. The proposed research is novel in the following three ways compared to previous research: First, the illuminative variations and shadow regions are reduced by an illumination normalization based on the median and inverse filtering of the L*a*b* image. Second, the multiple occluded and overlapped people are tracked by combining the GMM in the still image and the Lucas-Kanade-Tomasi (LKT) method in successive images. Third, with the proposed human tracking and the existing face detection & recognition methods, the tracked multiple people are successfully identified. The experimental results show that the proposed method could track and recognize multiple people with accuracy.

• 디지털융복합연구
• /
• 제11권12호
• /
• pp.295-302
• /
• 2013

사람 검출은 정지된 영상 혹은 동영상으로부터 사람의 움직임이나 자세를 추정하고, 사람이 찾아질 경우 영상 내 사람의 좌표, 동작 인식, 보안관련 인증 등을 알아내는 기술로 정의된다. 이러한 사람 검출은 다른 객체의 검출이나 사람과 컴퓨터와의 상호작용, 동작 인식 등의 기초 기술로서 해당 시스템의 성능에 영향을 미치는 매우 중요한 변수 중에 하나이다. 그러나 영상 내의 사람은 움직임, 자세, 크기, 빛의 방향 및 밝기, 다른 객체와의 중복 등의 환경적 변화로 인해 사람 모양이 다양해지므로 정확하고 빠른 검출이 어렵다. 따라서 본 논문에서는 피셔의 선형 판별 분석을 이용하여 몇 가지 환경적 조건을 극복한 정확하고 빠른 사람 검출 방법을 제안한다. 제안된 방법은 사람 움직임 및 자세와 배경에 무관하게 빠른 시간 안에 사람을 검출하는 것이 가능하다. 이를 위해 계층적인 방법으로 사람 검출을 수행하며, 휴리스틱한 방법, 피셔의 판별 분석을 이용하여 사람 검출을 수행하고, 검색 영역의 축소와 선형 결정의 계산 시간의 단축으로 검출 응답 시간을 빠르게 하였다. 추출된 사람 영상에서 사람의 자세를 추정하고 사람의 영역을 검출함으로써 사람 정보의 사용에 있어 보다 많은 정보를 추출할 수 있도록 하였다.

• 한국생활과학회지
• /
• 제11권4호
• /
• pp.347-355
• /
• 2002

The purpose of this study was to find possible solutions to the aged-related problem that is emerging as one of serious social issues in Korea by investigating the images young people have toward the aged. The questionnaire-based survey for this study was conducted with 643 middle school students representing teens and 523 undergraduates representing young people in the twenties, who were 592 from Daegu and 574 from Gwangju. It was carried out from December 2000 to March 2001. The data were analyzed in frequency(N), percentage(%), mean(M) and standard deviation(SD) through the SPSSWIN 10.0 program, $x^2-test$ and reliability test. The findings are summarized as follows. 52.5% of respondents reported that they had the experience in living together with their grandparents, while the number of respondents currently living together with their parents just accounted for 17.6%. In the question about the sense of value for family life, it was shown that the traditional idea that an eldest son or other son has the duty of supporting parents was positively changed to one that any of sons or daughters may support parents. The entire image toward the aged appeared to be positive with the mean value of 3.62. Things associated with the aged were the respect-for-aged house and a stick in that order. The images young people perceive towards the aged were largely divided into the 13 items image including the community centers for the aged.

• 한국의류학회지
• /
• 제19권2호
• /
• pp.287-296
• /
• 1995

measuring surface area errors can be brought about with different measuring people. This study aims at eliminating such errors in measurement. With measures by 3 people whose experience varies from person to person, the existing area measuring method using a planimeter and two other methods which use a computer (one using a digitizer and the other using a scanner) have been analyzed and compared. Three methods have not shown a meaningful difference in respect to the value" of area and two methods other than the one using a scanner have shown a meaningful difference among 3 measuring people. Therefore, we propose the method using a scanner by image processing should be a more improved one for area measuring. The arguments for that are as fllows. 1. The operation for measurement is simple and it has a high degree of accuracy with few errors. 2. Because different measuring people cause few errors the operation started by one person can be handed over to anyone else and the operation dosen't require previous skill. 3. Once image file is saved, the operation can be performed on several computers at the same time with seperate part on each computer. 4. Three methods have needed nearly the same length of time, but time for the method using a scanner can be reduced on computers with a higher capacity.th a higher capacity.

• 디지털콘텐츠학회 논문지
• /
• 제19권2호
• /
• pp.245-250
• /
• 2018

영상처리 기술은 현대 사회에서 다양한 분야에 응용될 수 있다. 현대인들이 관심을 가지고 있는 헬스케어도 그 분야 중 하나이다. 운동기구등을 가지고 하는 헬스케어는 정확한 동작이 우선시 되어야 하는데, 일반인들은 비용의 문제 등으로 혼자서 운동을 하고 있는 실정이다. 이러한 경우에는 운동의 효율성을 보장할 수 없고, 때에 다라서는 운동자에게 역효과가 나기도 한다. 본 논문에서는 영상처리 기술을 이용하여 일반인이 혼자서 운동을 할 때 자세를 잡아 주고 교정해 주는 프로그램을 개발하였다. 사용자들은 운동 시 본 프로그램을 통하여 정확한 자세를 가르치는 개인트레이너를 고용하는 효과를 얻을 것으로 기대한다.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.147-153
• /
• 2023

In recent times, an absence of effective crowd management has led to numerous stampede incidents in crowded places. A crucial component for enhancing on-site crowd management effectiveness is the utilization of crowd counting technology. Current approaches to analyzing congested scenes have evolved beyond simple crowd counting, which outputs the number of people in the targeted image to a density map. This development aligns with the demands of real-life applications, as the same number of people can exhibit vastly different crowd distributions. Therefore, solely counting the number of crowds is no longer sufficient. CSRNet stands out as one representative method within this advanced category of approaches. In this paper, we propose a crowd counting network which is adaptive to the change in the density of people in the scene, addressing the performance degradation issue observed in the existing CSRNet(Congested Scene Recognition Network) when there are changes in density. To overcome the weakness of the CSRNet, we introduce a system that takes input from the image's information and adjusts the output of CSRNet based on the features extracted from the image. This aims to improve the algorithm's adaptability to changes in density, supplementing the shortcomings identified in the original CSRNet.

• 한국치위생학회지
• /
• 제7권2호
• /
• pp.197-211
• /
• 2007

The purpose of this study was to examine the image of dental hygienists. The subjects in the study were 396 patients and their caregivers who visited 14 dental hospitals and dentists' offices in and around Seoul. After a survey was conducted, the following findings were given: 1. The people investigated gave a mean of 4.0 to the image of dental hygienists. Dental hygienists rated highest in terms of looking neat and tidy(4.33), and were given the lowest marks in arbitrary job performance(3.46). 2. There appeared four different types of dental hygienist images, which made a 59.824 prediction of the image of dental hygienists in general. A typical image(4.11) was most dominant, followed by professional one(4.07), personal one(4.01) and social one(3.73). 3. The relations between the general characteristics of the respondents and their image of dental hygienists could be described as below: 1) By age, those who were in their 60s(4.12) had the best image of dental hygienists, and the teenagers(3.90) had the worst image of them. 2) By gender, the men(4.05) looked at dental hygienists more positively than the women(3.96). They had a significantly different opinion on the social image of dental hygienists according to gender(pE0.05). 3) By marital status, the married people(4.00) had a better image of dental hygienists than the unmarried ones(3.95). 4) As for the influence of the type of dental institutions, they had a more favorable image of dental hygienists in dentists' offices(4.13) than in dental hospitals(3.88). There was a broad significant difference in the way they looked at the professional and personal images of dental hygienists according to the type of dental institutions(pE0.001). 5) As to the impact of educational level, those who received community-college or higher education(4.01) had the best image of dental hygienists, and those who received middle-school or lower education(3.91) had the worst image of them. 6) By occupation, the government workers and students(4.07) had the best image of dental hygienists, and the company employees(3.90) had the worst image of them. They took a significantly different view of the social image of dental hygienists according to occupation(pE0.05). 7) Concerning the impact of the frequency of receiving dental treatment, the respondents who had received it seven times or more(4.16) had the best image of dental hygienists, and those who hadn't(3.79) the worst image of them. There was a wide significant gap according to that frequency. The way they looked at the typical, social and professional images of dental hygienists was quite different significantly according to that frequency as well(pE0.001). 8) As for the influence of whether they were accompanied by caregivers or not, the people who weren't accompanied by caregivers(3.99) had a better image of dental hygienists than those who were(3.97).

• 한국의류산업학회지
• /
• 제17권3호
• /
• pp.382-391
• /
• 2015

People are exposed to diverse images and naturally find images to express themselves to others for personalsatisfaction. They present ideal images that they desire to obtain or actual images that they already have. People find differences between ideal images and actual images as well astry to overcome differences by managing appearance or purchasing fashion items. The congruence between real and ideal self-images and perceived body images stimulate clothing involvement or consumer confidence to influence fashion innovativeness and fashion opinion leadership. Fashion leaders are known for confidence when making buying decisions on new fashion products and are more likely to influence other consumers to buy new items. This study useda structural equation model to understand the influence of perceived self and body image on clothing involvement and consumer confidence as well as define how perceived images influence fashion leadership through clothing involvement and consumer confidence. The results of this study indicated that self-image congruence has a positive impact on social body image and personal body image. A positive influence of perceived body image on clothing involvement and consumer confidence was also detected. Fashion opinion leadership could be explained by clothing involvement and consumer confidence; however, fashion innovativeness could only be explained by consumer confidence.

• 복식문화연구
• /
• 제9권5호
• /
• pp.734-746
• /
• 2001

The purpose of this study is to investigate the influence of women's self-image on image evaluation of clothing self-image, and on their selection of clothing styles by situations. The subject of investigation was 500 women above 20 living in Daegu. 6 types of clothing styles including classic, casual, elegant, dramatic, romantic, and mannish and 7 social situations including shopping near house, shopping in a busy street, cultural center, wedding ceremony, dinning out, alumni meeting or fraternity meeting, and couples meeting were used for this study. Data analysis was performed using SPSS package, which included factor analysis, reliability test, cluster analysis, ANOVA, and X²-test. The results are summarized as follows. 1. Adult women could be classified into 4 groups such as the passive mannish, the passive feminine, the active mannish, and the active feminine by their self-images. 2. There were different opinions on each clothing style by self-image. In the image of each clothing style by self-image groups, the passive feminine group considered classic style having effect to make people look tall, mature and elegant style to make people look active and charming. Also, they rated the boldness of dramatic style and the activeness of mannish style high. The active feminine group estimated the boldness of mannish style high. 3. Selection of clothing style differed according to various situations. More formal the situation was, more classic style tended to be selected and for less formal situation, mannish style was selected.