• The Journal of Korea Robotics Society
• /
• v.8 no.1
• /
• pp.1-7
• /
• 2013

Body gesture Recognition has been one of the interested research field for Human-Robot Interaction(HRI). Most of the conventional body gesture recognition algorithms used Hidden Markov Model(HMM) for modeling gestures which have spatio-temporal variabilities. However, HMM-based algorithms have difficulties excluding meaningless gestures. Besides, it is necessary for conventional body gesture recognition algorithms to perform gesture segmentation first, then sends the extracted gesture to the HMM for gesture recognition. This separated system causes time delay between two continuing gestures to be recognized, and it makes the system inappropriate for continuous gesture recognition. To overcome these two limitations, this paper suggests primitive body model encoding, which performs spatio/temporal quantization of motions from human body model and encodes them into predefined primitive codes for each link of a body model, and Selective/Asynchronous Input-Parallel State machine(SAI-PSM) for multiple-simultaneous gesture recognition. The experimental results showed that the proposed gesture recognition system using primitive body model encoding and SAI-PSM can exclude meaningless gestures well from the continuous body model data, while performing multiple-simultaneous gesture recognition without losing recognition rates compared to the previous HMM-based work.

• Korean Journal of Human Ecology
• /
• v.11 no.1
• /
• pp.59-67
• /
• 2002

The purpose of this study was to investigate the recognition and satisfaction of the lower body shapes of male college students. The subjects in this study were 178 male college students. The results were as follows: 1. The degree of recognition and satisfaction of girth items in lower part of the body scored average. Subjects tended to be dissatisfied with their height. 2. The degree of satisfaction of waist girth and weight was influenced by the real body size than the degree of recognition. And abdomen girth, hip girth, ankle girth, leg length, hight, crotch length were affected by the degree of recognition than the real body size. 3. Subjects were more satisfied with standard lower body type than with lean and obese ones.

• Korean Journal of Human Ecology
• /
• v.23 no.6
• /
• pp.1171-1189
• /
• 2014

In order to provide the basic data for creating the environment which can efficiently reflect prefer fit along with body size when selecting clothes size in the indirect purchasing environment, this study analyzed the difference of ready-made jacket part-specific fit preferred by fashion models in their twenties and female college students. This study was to analyze the impact of body size, recognition of body part-specific characteristics shape, body satisfaction on prefer fit of jacket. As for the difference of prefer fit depending on the body size, female college students preferred more loose fit than models. The difference according to recognition of body part-specific characteristics shape turned out to be significant for prefer fit depending on the degree of bend of neck, arm length, bend of back recognition and matching fit was found to be preferred as they recognize their body shape to be normal and the difference according to body satisfaction appeared to be significant in the terms of bend of back, hip width/protrusion, torso size/length, sleeve length, whole body shape and they turned out to prefer matching fit as they are satisfied with their body. As shown above, body size, recognition of body part-specific characteristics shape, especially body satisfaction have a great influence on prefer fit of jacket and therefore, if preparing for a size selection step according to body shape and satisfaction in the jacket size selection process, customers' satisfaction in jacket size may be improved and it is considered to be helpful for both consumers and sellers.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.214-216
• /
• 2006

Expressive face and human body gestures are among the main non-verbal communication channels in human-human interaction. Understanding human emotions through body gesture is one of the necessary skills both for humans and also for the computers to interact with their human counterparts. Gesture analysis is consisted of several processes such as detecting of hand, extracting feature, and recognizing emotions. Skin color information for tracking hand gesture is obtained from face detection region. We have revealed relationships between paricular body movements and specific emotions by using HMM(Hidden Markov Model) classifier. Performance evaluation of emotional human body recognition has experimented.

• The Research Journal of the Costume Culture
• /
• v.12 no.3
• /
• pp.485-496
• /
• 2004

The purpose of this study conducted a survey on 356 men in their twenties to investigate their recognition of their bodies. Also physical measurements were conducted on them and the lower parts of the bodies were classified into several types. The study examined the relevance of the subjects' recognition of their bodies to the physical types of the lower parts of the body. The results can be summarized as follows; There are four factors that constitute the physical shapes of the lower parts of the body and the lower parts of the body are classified into three physical types by cluster analysis. In terms of the degree of recognition of lower parts of the body shapes, the respondents' recognition of their bodies was similar to the actual measurements except for heights and leg lengths regardless of physical types, showing that they recognized well their actual physical types. With respect to the degree of satisfaction with body types, the surveyed were dissatisfied with thick circumference items and short length items. The actual measurements and the degree of recognition showed significant correlations in almost all the items while the actual measurements and the degree of satisfaction showed significant negative correlation in the circumference items. The degree of satisfaction with heights showed significant correlations with almost all measurements, demonstrating that the degree of satisfaction of the males in their twenties with the lower pats of body has closer correlations with the height items of the actual measurements that the circumference items. The degree of satisfaction with bodies was more dependent on people's recognition than the actual measurements.

• The Korean Journal of Food And Nutrition
• /
• v.24 no.3
• /
• pp.386-395
• /
• 2011

The purpose of this research was to study food behaviors and nutrient intakes according to body mass index(BMI) and body image recognition in 211 female university students in Incheon. The majority of the surveyed subjects were in the normal range for BMI. Most of these female university students preferred a thin body type and were not satisfied with their body shapes. Most also controlled their body weight for appearance by exercising and limiting food intake. The obese group often ate processed foods(p<0.01) and ate out(p<0.05). The underweight group and normal-weight group took vitamins and supplements more frequently(p<0.001). Those students who recognized their body image as a 'fat shape' had good appetites(p<0.05) and those who recognized themselves as 'normal shape' considered food formulations ate every meal (p<0.05) and consumed vitamins and other supplements frequently(p<0.01). The mean calorie intake of all students was about 80% of the recommend amount, so there was a risk of lack of various nutrients. The 'fat' students by body image recognition had lower calorie intakes in order to reduce body weight. In all the groups, there was a lack of vitamins $B_1$ and $B_2$, as well as the minerals Ca and Fe. Therefore, education on correct body image recognition and training on proper weight control are deemed necessary. In addition, education and counseling on nutrition that are tailored to individual status are needed.

• Asian-Australasian Journal of Animal Sciences
• /
• v.18 no.8
• /
• pp.1194-1198
• /
• 2005

A computer vision system was designed and validated to recognize an individual Holstein cattle by processing images of their body patterns. This system involves image capture, image pre-processing, algorithm processing, and an artificial neural network recognition algorithm. Optimum management of individuals is one of the most important factors in keeping cattle healthy and productive. In this study, an image-processing system was used to recognize individual Holstein cattle by identifying the body-pattern images captured by a charge-coupled device (CCD). A recognition system was developed and applied to acquire images of 49 cattles. The pixel values of the body images were transformed into input data comprising binary signals for the neural network. Images of the 49 cattle were analyzed to learn input layer elements, and ten cattles were used to verify the output layer elements in the neural network by using an individual recognition program. The system proved to be reliable for the individual recognition of cattles in natural light.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.29 no.9_10 s.146
• /
• pp.1316-1328
• /
• 2005

The purpose of this study was to compare the differences in recognition of sexy body parts and apparel designs by gender and correlations between sexy body parts and apparel designs. Data were collected through a survey of 265 males and 303 females. Data were analyzed by included t-tests, f-tests, and Pearson's correlations. The results were as follows: 1. Females found male body parts were sexier than males did. Males found female body parts were sexier than females did. 2. Females found men's clothing designs were sexier than males did. Also, males recognized women's clothing designs as sexier than females did. 3. Males found see-through and body-consciousness, the methods of designing sexy styles, were sexier than females did. Differences in sexy color recognition by gender were also found. 4. There were correlations between most of sexy body parts and designs which emphasized that body parts. The results of this study shows the differences in recognition and correlation by gender. The results may be applied to develope sexy designs for different genders.

• Korean Journal of Human Ecology
• /
• v.14 no.5
• /
• pp.847-858
• /
• 2005

The purpose of this study was to compare the differences in recognition of sexy body parts and apparel designs by age and to discover the correlations between sexy body parts and apparel designs. Data were collected through a survey of 265 males and 303 females. Analyses included t-tests, f-tests, and Pearson's correlations. The results were as followings; 1. The 20's-30's age group found female body parts were sexier than 40's-50's did. 20's-30's believed the male body was sexier than 40's-50's did. 2. The age groups found men's clothing designs were different by different age groups. Also, differences in female clothing designs were recognized by different age groups. 3. The 40's-50's age group recognized see-through sexier than 20's-30s did. Differences in sexy color recognition by age were also found. 4. There were correlations between most of sexy body parts and designs which emphasized the body parts. The results of this study show the differences in recognition and correlation by age. The results may be applied to developing sexy designs for different targeted age groups.