• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1018-1030
• /
• 2013

The corpus callosum is the largest connective structure in the brain, and its shape and size are correlated to sex, age, brain growth and degeneration, handedness, musical ability, and neurological diseases. Manually segmenting the corpus callosum from brain magnetic resonance (MR) image is time consuming, error prone, and operator dependent. In this paper, two semi-automatic segmentation methods are present: the active contour model-based approach and the active shape model-based approach. We tested these methods on an MR image of the human brain and found that the active contour approach had better segmentation accuracy but was slower than the active shape approach.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.27 no.1
• /
• pp.100-110
• /
• 2003

The purpose of this study were 1) to find out the structural elements in classifying clothes images, and 2) to segment the consumer market for women's street clothes based on clothes image preferences and to identify the group differences in psychological variables, purchasing behavior variables and demographic variables. The sample was taken from 1106 middle class women who were in thier 30's∼40's living in Gwangju city. Consumers were classified into six groups: active image group (35.4%), feminine image group (25.9%). daring image group (16.5%), elegant image group (10.8%), dressy image group (8.9%) and brisk image group (3.5%). Women in their 30's∼40's preferred elegant image, daring image, active image and feminine image. Elegant image oriented group: This group is the lowest education level group and has the highest rating of housewife. This group has the lowest scores use of person information search, Daring image oriented group: Woman in their 30's prefers daring image. This group thinks practical benefit sought is less important than self-expression benefit sought. This group has the highest scores use of non-person information search, Active image oriented group: This group is practical benefit seeking group. and purchases the lowest amount of clothes. The amount of average household income is the lowest. Feminine image oriented group: The amount of average household income is the highest. This group perceives more youth$.$fashion benefit sought and self-expression benefit sought than elegant image oriented group. ANOVA, $\chi$$^2$-test revealed differences among groups according to benefit sought use of information sources, purchasing behavior variables and demographic variables.

• Journal of Fashion Business
• /
• v.17 no.2
• /
• pp.164-178
• /
• 2013

The purpose of this study is to verify effects of female college students' self-image on appearance management behavior and investigate the differences caused by TV involvement and entertainer imitation on the appearance managing behavior. Respondents of the survey were 424 college females living in Seoul and Gyeonggi province. For statistical analysis, factor analysis and multiple regression were conducted using SPSS 18.0 program. The results of this study are as follows: First, self-image among college females were composed of 5 factors, which were active image, feminine image, intelligent image, gentle image and modern image. Second, college females' self-image influenced on skin management behavior, hair management behavior, make-up behavior, clothing behavior and weight management behavior significantly. Specifically, as respondents' active image and modern image are getting higher, they tend to perform skin management behavior, hair management behavior and clothing behavior. As female students' intellectual image and modern image were getting higher, more positive effects were found on make-up behavior. As female students' gentle image and active image were getting higher, there was more positive effects on weight management behavior. But, female students' self-image didn't show significant effects on cosmetic surgery behavior. Third, when subjects' TV involvement was high, self-image made greater effect on skin management behavior and cosmetic surgery behavior than those with low TV involvement. Forth, when entertainer imitation was high, self-image made greater effects on skin management behavior, hair management behavior, clothing behavior, make-up behavior, weight management behavior, cosmetic surgery behavior than those with low entertainer management.

• The Research Journal of the Costume Culture
• /
• v.26 no.6
• /
• pp.872-887
• /
• 2018

This study aims to identify the differences between Korean and Chinese and males and females in terms of female image preferences. The survey was conducted for 1 month targeting male and female Korean and Chinese subjects. Among the 350 completed questionnaires, 309 were used for analysis. For the analysis, 11 female images were chosen based on theoretical study, then a t-test and a paired t-test were carried out using SPSS 19.0. The results of this study are as follows: First, differences in female image preferences were observed to depend on nationality and gender. Koreans prefer urban images while Chinese prefer cute, intelligent, and sexy images. Second, males prefer innocent or sexy images, while females prefer sophisticated images. Third, Korean males prefer innocent, active, sophisticated, gentle, cute, sexy, urban, natural, intelligent, spectacular, and neutral images in order. Chinese males prefer gentle, innocent, sexy, active, sophisticated, intelligent, cute, natural, urban, spectacular, and neutral images in order. Fourth, Korean females prefer sophisticated, gentle, urban, natural, intelligent, innocent, active, sexy, cute, spectacular, and neutral images in order. Chines females prefer sophisticated, intelligent, cute, gentle, innocent, active, natural, sexy, urban, spectacular, and neutral images in order. Using these results, it will be possible to design marketing strategies for global consumers.

• Journal of Fashion Business
• /
• v.8 no.4
• /
• pp.141-155
• /
• 2004

The purpose of this study was to arrange the korean women's hair styles of the beginning of 21st century and make hair style image making chart to use personal image making consulting data through analyze actress hair styles of broadcasting TV drama. To accomplish this purposes, picked up the two most popular dramas per each broadcasting stations, KBS1, KBS2, MBC, SBS, in february 2004. and analyzed and arranged hair styles of actress and at the last made the hair style image making chart. The results of the research are as belows. 1. Hair trends of february 2004. were Modern Sophisticated, Active and Romantic. 2. The results of three classifications of hair style trends, form, color, accessory, were as belows. 1) Form : Layer, left part, straight, low wave, long hair, no volme, bang were in vogue. Generally, Modern Sophisticated, Active, Romantic feeling were in vogue. 2) Color : Black, brown, two tone color were in vogue. Generally Modern Sophisticated, Romantic, Active feeling were in vogue. 3) Accessory : Hair bands & pins were in vogue. Generally these gave the Modern, Active feeling. 3. Hair style image making chart manufacturing depends on fashion feeling. 1) Classification of feeling, 2) Analysis of form, 3) Analysis of color, 4) Hair style image making chart manufacturing depends on fashion feeling This research will be a historical data of korean women's hair styles of the beginning of 21st century & can be used the basic data of personal hair style image making consulting.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.6
• /
• pp.222-228
• /
• 2003

Lane departure avoidance system is one of the key technologies for the future active-safety passenger cars. The lane departure avoidance system is composed of two subsystems; lane sensing algorithm and active-steering controller. In this paper, the road image is obtained by vision sensor and the lane parameters are estimated using image processing and Kalman Filter technique. The active-steering controller is designed to prevent the lane departure. The developed active-steering controller can be realized by steer-by-wire actuator. The lane-sensing algorithm and active-steering controller are implemented into the steering HILS(Hardware-In-the-Loop Simulation) and their performance is evaluated with a human driver in the loop.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.314-323
• /
• 1999

This paper introduces a methodology of active calibration of a camera pose (orientation and position) using the images of cylindrical objects that are going to be manipulated. This active calibration method is different from the passive calibration where a specific pattern needs to be located at a certain position. In the active calibration, a camera attached on the robot captures images of objects that are going to be manipulated. That is, the prespecified position and orientation data of the cylindrical object are transformed into the camera pose through the two consecutive image frames. An ellipse can be extracted from each image frame, which is defined as a circular-feature matrix. Therefore, two circular-feature matrices and motion parameters between the two ellipses are enough for the active calibration process. This active calibration scheme is very effective for the precise control of a mobile/task robot that needs to be calibrated dynamically. To verify the effectiveness of active calibration, fundamental experiments are peformed.

• Journal of the Korean Society of Costume
• /
• v.59 no.3
• /
• pp.55-56
• /
• 2009

The purpose of this study was to analyse body and cosmetic image according to women's sex role identity. The subjects of this study were 433 women over 20 years old. Self-administered questionnaires were used for data collection. SPSS(Ver. 15.0) was used for mean, median, frequency, percentages, factor analysis, and one-way ANOVA. The results of this study were as followed; First, women were clustered into 4 groups according to their sex role identity. 36.5% was classified as an androgynous group, 32.4% was a undifferentiated group, 16.1% was a masculine group, and 15.0% was a feminine group. Second, factors of women's body image were interest in appearance, interest in weight, and charming of appearance. Factors of cosmetic image were natural & sociable, urban & intellect, passionate, romantic, prestige & sophisticate, fashionable & splender, active, feminine, and formal. Third, Androgynous group showed much interests in appearance and charming of appearance, but undifferentiated group had low interests. Androgynous group pursued natural & sociable, urban & intellect, passionate, romantic, prestige & sophisticate, fashionable & splendor, active, feminine, and formal images most when they applied make-ups. Masculine group pursued urban & intellect and active images much and femme group pursued natural & sociable, feminine, and formal images much. However undifferentiated group pursued all factors of cosmetic images less. Forth, androgynous group applied more kinds of cosmetics, but undifferentiated group applied less.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1044-1049
• /
• 2006

얼굴 추적은 Vision base HCI의 핵심인 얼굴인식, 표정인식 그리고 Gesture recognition등의 다른 여러 기술을 지원하는 중요한 기술이다. 이런 얼굴 추적기술에는 영상(Image)의 Color또는 Contour등의 불변하는 특징들을 사용 하거나 템플릿(template)또는 형태(appearance)를 사용하는 방법 등이 있는데 이런 방법들은 조명환경이나 주위 배경등의 외부 환경에 민감하게 반응함으로 해서 다양한 환경에 사용할 수 없을 뿐더러 얼굴영상만을 정확하게 추출하기도 쉽지 않은 실정이다. 이에 본 논문에서는 deformable한 model을 사용하여 model과 유사한 shape과 appearance를 찾아 내는 AAM(Active Appearance Model)을 사용하는 얼굴 추적 시스템을 제안하고자 한다. 제안된 시스템에는 기존의 Combined AAM이 아닌 Independent AAM을 사용하였고 또한 Fitting Algorithm에 Inverse Compositional Image Alignment를 사용하여 Fitting 속도를 향상 시켰다. AAM Model을 만들기 위한 Train set은 150장의 4가지 형태에 얼굴을 담고 있는 Gray-scale 영상을 사용 하였다. Shape Model은 각 영상마다 직접 표기한 47개의 Vertex를 Trianglize함으로서 생성되는 71개의 Triangles을 하나의 Mesh로 구성하여 생성 하였고, Appearance Model은 Shape 안쪽의 모든 픽셀을 사용해서 생성하였다. 시스템의 성능 평가는 Fitting후 Shape 좌표의 정확도를 측정 함으로서 평가 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.5
• /
• pp.1840-1855
• /
• 2015

Troubles are often met when traditional active contours extract boundaries of medical images with inhomogeneous bias and various noises. Focusing on such a circumstance, a localized mutual information active contour model is discussed in the paper. By defining neighborhood of each point on the level set, mutual information is introduced to describe the relationship between the zero level set and image field. A driving energy term is then generated by integrating all the information. In addition, an expanding energy and internal energy are designed to regularize the driving energy. Contrary to piecewise constant model, new model has a better command of driving the contours without initialization.