• Journal of Biomedical Engineering Research
• /
• v.30 no.3
• /
• pp.191-198
• /
• 2009

Phlegm smear testing for acid-fast bacilli (AFB) requires careful examination of tubercle bacilli under a microscope to distinguish between positive and negative findings. The biggest weakness of this method is the visual limitations of the examiners. It is also time-consuming, and mistakes may easily occur. This paper proposes a method of identifying tubercle bacilli that uses a computer instead of a human. To address the challenges of AFB testing, this study designs and investigates image systems that can be used to identify tubercle bacilli. The proposed system uses an electronic microscope to capture digital images that are then processed through feature extraction, image segmentation, image recognition, and neural networks to analyze tubercle bacilli. The proposed system can detect the amount of tubercle bacilli and find their locations. This paper analyzes 184 tubercle bacilli images. Fifty images are used to train the artificial neural network, and the rest are used for testing. The proposed system has a 95.6% successful identification rate, and only takes 0.8 seconds to identify an image.

• KIEAE Journal
• /
• v.11 no.2
• /
• pp.9-15
• /
• 2011

Many Korean palaces such as Deoksu Palace and Kyungbok Palace are located in downtown Seoul. Modern high-rise buildings around the palace have been the background scenery of traditional architecture in it. In this case, such landscapes mixed with traditional images and contemporary images can give a negative impression to visitors watching from inside the palace. In this study, we analysed the correlation between landscape image of Deoksu Palace and trees' view blockage of buildings around it with three independent variables. The first variable is completely blocked view of buildings around the palace by the trees. The second variable is half-blocked view of buildings around the palace by the trees. The third variable is the view of buildings around the palace that is not blocked by the trees. The analysis showed that there were some significant correlations between landscape image of Deoksu Palace and trees' view blockage of buildings around it. It also showed that the view blockage ratio by the trees has positive correlation with improvement of landscape image of the palace.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.6
• /
• pp.207-217
• /
• 2022

In recent years, the Iraqi market witnessed a large opening that resulted from the entry of many different products with an absence of government regulations. As a result, marketing deception practices have emerged as a new phenomenon. This study examines the effect of deceptive brand image on consumer purchase intention, with consumer attitude as a mediator. A quantitative method was applied in the form of a questionnaire distributed to shoppers at Carrefour Supermarket in Erbil, Kurdistan Region of Iraq. A random sampling technique was conducted. Subsequently, 200 questionnaires were distributed, and 175 valid questionnaires were analyzed, indicating an 87% response rate. Partial least squares structural equation modelling (PLS-SEM) has been utilized to test the hypothesis. The result showed that brand image deception has a negative impact on consumer purchasing intention. Also, attitude mediates the relationship between deceptive brand image and consumer purchase intention. The empirical finding confirms that deceptive marketing practices such as brand deception can change the attitude of consumers negatively toward brands and, therefore, affect the consumer purchase intentions. The findings suggest that honest brand marketing is beneficial in increasing the attitude toward the brand. This strategy will increase consumer purchase intentions.

• Korean Journal of Health Education and Promotion
• /
• v.19 no.4
• /
• pp.33-44
• /
• 2002

This study was conducted to investigate the relationship between an eating disorder, body image, depression and self-esteem amongst a subject group of 282 college women between Jan.,1st and 30th,2002, to provide base data for eating disorder levels of college women and to provide base data for health control. The evaluative instrument was a constructive questionnaire that consisted of 8 items of general characteristics and weight control questions, 24 questions relating to eating disorders, 17 questions pertaining to body image, 10 questions pertaining to depression and 10 questions pertaining to self-esteem. To identify the levels of an eating disorder, body image, depression and self-esteem perceived by subjects, the researcher used means and SDs. To test the significance of a subject's eating disorder, body image, depression and self-esteem according to the BMI, the researcher used the t-test. To test the correlation between the BMI, an eating disorder, body image, depression and self-esteem, the researcher used Pearson correlation coefficient. The results of this study are as follows. The mean score for anorexia nervosa was 31.52 and the mean score for bulimia nervosa was 24.12. Differences between the underweight group and the normal weight group in the level of eating disorders were significant (t=-6.94, p=.000). There were high positive correlations between the BMI and an eating disorder (r=.383, p<.01), between an eating disorder and depression (r=.161, p<.01), between body image and self-esteem (r=.653, p<.01). In addition, there were high negative correlations between an eating disorder and body image (r=-.214, p<01), between an eating disorder and self-esteem (r=-.196, p<.01), between depression and body image (r=-.541, p<.01), and between depression and self-esteem (r=-.537, p<.01). These results indicate that Korean college women need more education and counseling on dietary habits. Also, the systemic efforts reestablish the social standard of the beauty should be taken. Further empirical and experimental studies would be required for investigating for the factors influencing the eating attitude of the college women and discriminating the variables affecting the various specific dimensions of the eating attitude.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.10a
• /
• pp.439-444
• /
• 2003

The burial culture has prevailed in our county because of the effect of Confucianism. First of all, tombs've had an negative effect on the vista of national land and caused an ineffective use of national land recently. for this reason, the systematic management of the toms is necessary The purpose of this project is to identify tombs' geographical coordinates from orthoimage and to analysis algorithms for extracting tombs on the satellite image. We've used IKONOS image for those purpose, because it's very similar to KOMPSAT-2 image's characteristics which will be launched near future. and, It will make the best use of tombs management of each local government.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.185-188
• /
• 2001

의료 영상 처리 기술은 질병의 진단 및 치료를 위한 계획이나 방법을 결정하는데 있어 매우 중요한 역할을 하고 있다. 뇌 MR 영상에서의 질병 진단을 위한 전처리 단계로서 필수적으로 이루어져야 하는 단계가 영상 분할 단계이다. 본 논문에서는 뇌의 질병 진단에 사용할 수 있는 자료를 제공하기 위한 뇌 영상 분할 방법을 제시한다. T2 강조 영상의 반전된 영상에서 원본 영상을 뺀 차이 영상의 결과로 회백질·뇌척수액·비정상 영역이 두드러지게 나타나는 점을 이용해 회백질 뇌척수액·비정상 영역과 백질 영역을 분리하는 방법을 제안한다. 또한 뇌척수액 영역의 위치 정보와 몇 가지 특징들을 정의하여 분할되어진 회백질·뇌척수액· 비정상 영역에서 뇌척수액 영역만을 분할하는 방법을 제시한다. 600 여 개의 T2 강조 영상에 대해서 실험을 행하러 비교적 정확한 분할 결과를 유도할 수 있었음을 확인하였다.

• Journal of Environmental Science International
• /
• v.14 no.10
• /
• pp.905-910
• /
• 2005

The purpose of this study is the comparative analysis of Susan citizens' images of Eulsook-do as a coastal tourism destination before and after the construction of a road bridge across the Nakdong estuary in order to analyze local people's changes in leisure patterns. Analysis of the images of a pre-construction Eulsook-do that people aged both 40 and less and 50 and more had on five dimensions showed values higher than zero(0) that suggests neutral image, while their images of a post-construction Eulsook-do showed the shrinking size of pentagon on all five dimensions: ET(Entertainment), CA(Culture & Art), EE(Environment & Ecology), RC(Recreation) and LP(Leports) dimensions. Its pre- and post- construction image analysis conducted 20 years after it came to be built finds that the road bridge construction has led to the ecological, environmental disruption of the coast and the lower Nakdong river, having negative influence on the images of Eulsook-so.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.2
• /
• pp.95-102
• /
• 2011

In this paper, we propose measurement-devices for the assessment of input vector consisted of face's movement as feature points through image processing based on AAM technique. The proposed method has been applied to classify students by 2-class(ADHD positive, ADHD negative). Experimental results show that the proposed method was successful in acquiring more objective and quantitative data than conventional methods, it takes advantage of examining without temporal and spatial constraints.

• Journal of Microbiology
• /
• v.34 no.4
• /
• pp.300-304
• /
• 1996

To define the effects of zooplankton and phytoplankton to bacteria, bacterial numbers, frequency of dividing cells (FDC) and size distribution were performed with image analysis in the surface layer of Lake Soyang. In August 1992, when Anabaena was blooming, the bacterial number increased at daytime. Bacterial numbers and FDC value had a negative correlation (r = 0.83, P < 0.01). Bacterial size spectrums were dynamically changed during the day and night, especially the small bacteria less than $0.5\;{\mu}m^3$. Meanwhile, in October, after the bloom, the bacterial number was only one third of that in August, even though the FDC was higher than that in August. The bacterial numbers of small size class dropped at 13:00. But the size spectrums were relatively constant during the night time. These results suggest that the bacterial growth was tightly coupled with phytoplankton during Anabaena bloom. And after the bloom, the bacterial number was controlled grazing activity of zooplankton at daytime.