• Asia pacific journal of information systems
• /
• v.27 no.1
• /
• pp.38-53
• /
• 2017

As sensor technologies and image processing technologies make collecting information on users' behavior easy, many researchers have examined automatic emotion recognition based on facial expressions, body expressions, and tone of voice, among others. Specifically, many studies have used normal cameras in the multimodal case using facial and body expressions. Thus, previous studies used a limited number of information because normal cameras generally produce only two-dimensional images. In the present research, we propose an artificial neural network-based model using a high-definition webcam and Kinect to recognize users' emotions from facial and bodily expressions when watching a movie trailer. We validate the proposed model in a naturally occurring field environment rather than in an artificially controlled laboratory environment. The result of this research will be helpful in the wide use of emotion recognition models in advertisements, exhibitions, and interactive shows.

• Journal of Korea Game Society
• /
• v.17 no.5
• /
• pp.133-142
• /
• 2017

Recently, screen climbing contents such as sports climbing learning program and screen climbing games. Especially, there are many researches on screen climbing games. In this paper, we propose the skeleton correction method based on the body area of a climber to improve the posture recognition accuracy. The correction method consists of the modified skeletal frame normalization with abnormal skeleton joint filtering, the classification of body area into joint parts, and the final skeleton joint correction. The skeletal information obtained by the proposed method can be used to compare the climber's posture and the ideal climbing posture.

• Korean Journal of Community Nutrition
• /
• v.12 no.1
• /
• pp.3-12
• /
• 2007

This study was performed to investigate the body image perception by BMI and the dietary behaviors in 803 college students(408 males and 395 females). The degree of obesity was divided into an underweight group with BMI less than $18.5kg/m^2$, a normal group with BMI of $18.5{\sim}22.9kg/m^2$, an overweight group with BMI of $23{\sim}24.9kg/m^2$ and an obese group with BMI over $25.0kg/m^2$. The average ages of subjects were 22.9 years in males and 20.2 years in females. The average weight and height of male subjects were 175.3 cm and 69.6 kg, respectively and those of female subjects were 162.5 cm and 52.0 kg, respectively. The average BMIs of male and female subjects were $22.6kg/m^2$ and $19.7kg/m^2$, respectively. The distribution of subjects who perceived their current body image as ideal body image was 25.7% in males and 10.9% in females, showing that the body image satisfaction of male subjects was 1.5 times higher than that of female subjects. Body image perception for their own bodies was mostly shown as the average or standard shape both in males and females with 64.2% and 54.2%, respectively, but males showed a higher perception rate than females and 31.1% of females and 19.5% of males perceived their bodies as lean shape(p<0.01). The body image satisfaction was 4.20 in males and 3.70 in females, showing more satisfaction in the male subjects(p<0.001). The correlation between body image and physical variables in male subjects indicated that CBI and IBI showed statistically significant correlation and also BMI showed statistically significant correlation with IBI(p<0.001) and CBI(p<0.001). The frequency of eating out increased as the frequency of skipping meals increased(p<0.001) and the frequency of having snacks increased as the frequency of eating out increased(p<0.01). The correlation between body image and physical variables in female subjects showed that CBI and IBI(p<0.001) had statistically significant correlation. Body weight showed statistically significant correlation with CBI(p<0.001), BMI(p<0.001) and height(p<0.001). The frequency of eating out increased as height(p<0.01) and the frequency of skipping meals(p<0.001) increased. When both male and female subjects wanted leaner body shapes, they preferred much leaner shapes despite their current body images belonging in the normal range. Additionally subjects preferred the body image in the normal range in cases when their current body images were lean. In particular, more female subjects had strong desires to become leaner in their body images than male subjects, which could be analyzed as a risk factor for physical him. From the above results, it is considered that both male and female subjects need to establish proper recognition and dietary behaviors for their body images and also need nutritional education and counseling for desirable weight control methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.63-71
• /
• 2008

In this paper, we propose a color based hierarchically propagated particle filter that extends the color based particle filter into the articulated upper body tracking. Since color feature is robust to partial occlusion and rotation, the color based particle filter is widely used for object tracking. However, in articulated body tacking, it is not desirable to use the traditional particle filter because the dimension of the state vector usually is high and thus, many samples are required for robust hacking. To overcome this problem, we use a hierarchical tracking method for each body part based on the blown body part. By using a hierarchical tracking method, we can reduce the number of samples for robust tracking in the cluttered environment. Also for human pose recognition, we classify the human pose into eight categories using Support Vector Machine(SVM) according to the angle between upper- arm and fore-arm. Experimental results show that our proposed method is more efficient than the traditional particle filter.

• Journal of Korean Home Economics Education Association
• /
• v.18 no.2 s.40
• /
• pp.97-110
• /
• 2006

The purpose of this study was to investigate body image, nutritional knowledge and nutrient intakes of middle school students according to obesity index. In body image awareness, about half of the total subjects recognized their body image correctly. Perceived nutrition knowledge is higher in female students than in male students; however there was no difference about accuracy. All groups had a higher protein intake than recommended levels. In examining the correlation of each factors, there was a significant correlation between satisfaction of body weight and body image recognition(p<0.01).

• Journal of the Korean Society of Food Culture
• /
• v.36 no.2
• /
• pp.184-197
• /
• 2021

This study investigated the recognition and utilization status of food labeling and nutrition labeling, according to the body type recognition of university students. In a total of 351 subjects, the male subjects comprised of 25.8% belonging to the underweight awareness group, 46.3% normal weight awareness group, and 27.9% overweight awareness students. Among the female students, 29.2% belonged to the underweight awareness group, 36.6% were normal body weight, and 34.2% were the overweight group. When purchasing processed foods, the price (4.05 points), expiration date (4.03 points), and gross weight (3.88 points) were the most considered factors of the food labeling content (5 points) for all body shape recognition groups. The food labeling of canned foods was checked most by the underweight awareness group (p<0.05). For bread and snacks, the contents of food labeling were confirmed most by the normal weight awareness group and the overweight awareness group (p<0.001). For beverages, the normal weight awareness group checked more food labels (p<0.01). The underweight awareness group (55.2%) hardly checked the nutritional labeling, and 22.9% of these subjects did not check at all. Our results may provide the necessity to improve the incorrect eating habits of students, by evaluating differences between the cognitive body type and the actual body type by BMI.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.111-118
• /
• 2022

In computer vision research, the two-dimensional human pose is a very extensive research direction, especially in pose tracking and behavior recognition, which has very important research significance. The acquisition of human pose targets, which is essentially the study of how to accurately identify human targets from pictures, is of great research significance and has been a hot research topic of great interest in recent years. Human pose recognition is used in artificial intelligence on the one hand and in daily life on the other. The excellent effect of pose recognition is mainly determined by the success rate and the accuracy of the recognition process, so it reflects the importance of human pose recognition in terms of recognition rate. In this human body gesture recognition, the human body is divided into 17 key points for labeling. Not only that but also the key points are segmented to ensure the accuracy of the labeling information. In the recognition design, use the comprehensive data set MS COCO for deep learning to design a neural network model to train a large number of samples, from simple step-by-step to efficient training, so that a good accuracy rate can be obtained.

• Journal of Korea Multimedia Society
• /
• v.14 no.8
• /
• pp.992-999
• /
• 2011

This paper proposed a human body posture recognition program based on haar-like feature and hand activity detection. Its distinguishing features are the combination of face detection and motion detection. Firstly, the program uses the haar-like feature face detection to receive the location of human face. The haar-like feature is provided with the advantages of speed. It means the less amount of calculation the haar-like feature can exclude a large number of interference, and it can discriminate human face more accurately, and achieve the face position. Then the program uses the frame subtraction to achieve the position of human body motion. This method is provided with good performance of the motion detection. Afterwards, the program recognises the human body motion by calculating the relationship of the face position with the position of human body motion contour. By the test, we know that the recognition rate of this algorithm is more than 92%. The results show that, this algorithm can achieve the result quickly, and guarantee the exactitude of the result.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.153-160
• /
• 2020

The purpose of this study is to investigate the effect of female college students' participation in dance sports, perception of body attractiveness, and importance of body attractiveness. For this study, female university students residing in Gwangju Metropolitan City and Jeonnam region in 2019 were selected as the population. A total of 350 people were selected as the study subjects, but 170 dance sports participants and 130 non-participants were selected for the study, excluding 50 copies of double written and unfaithful data. After individually entering coded data into the computer, the statistical program (SPSS Windows.20.0 Version) was used. The results obtained through this research process are as follows. First of all, it was found that there was a difference in perception of body attractiveness depending on whether female university students participated in dance sports. Second, it was found that there was a difference in the importance of physical attractiveness depending on whether female college students participated in dance sports. Third, it was found that female college students' perception of body attractiveness has an effect on the importance of body attractiveness.

• The Journal of the Korea Contents Association
• /
• v.14 no.1
• /
• pp.24-29
• /
• 2014

This paper proposes a kinect-based human motion recognition model for the 3D contents control after tracking the human body gesture through the camera in the infrared kinect project. The proposed human motion model in this paper computes the distance variation of the body movement from shoulder to right and left hand, wrist, arm, and elbow. The human motion model is classified into the movement directions such as the left movement, right movement, up, down, enlargement, downsizing. and selection. The proposed kinect-based human motion recognition model is very natural and low cost compared to other contact type gesture recognition technologies and device based gesture technologies with the expensive hardware system.