• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• pp.823-831
• /
• 2019

In recent years, there has been developed systems such as a surveillance system and access control using a face recognition function instead of a password or an RFID chip, thereby reducing the risk of falsification. Moreover, deep learning technology has been applied to real-time face recognition technology in video, so it makes possible the development of access control system that improves the accuracy of recognition and efficiency of management. In this paper, we propose a real-time access management system based on face recognition using ResNet. The system is based on web server, which make it possible to manage the access by recognizing the person of the image through the camera and access information stored in the database. It can be accessed by a user application to receive various information. The implemented system identifies a person in real time and allows access control by accurately distinguishing whether they are members or not, and the test results can recognize in 0.2 seconds. The accuracy of recognition rate is up to about 97% depending on the experiment environment. With this system, access can be managed quickly and effectively, even many people rush to it.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.127-136
• /
• 2021

Real-time human recognition is a challenging task, as the images are captured in an unconstrained environment with different poses, makeups, and styles. This limitation is addressed by generating several facial images with poses, makeup, and styles with a single reference image of a person using Generative Adversarial Networks (GAN). In this paper, we propose deep learning-based human recognition using integration of GAN and Spatial Domain Techniques. A novel concept of human recognition based on face depiction approach by generating several dissimilar face images from single reference face image using Domain Transfer Generative Adversarial Networks (DT-GAN) combined with feature extraction techniques such as Local Binary Pattern (LBP) and Histogram is deliberated. The Euclidean Distance (ED) is used in the matching section for comparison of features to test the performance of the method. A database of millions of people with a single reference face image per person, instead of multiple reference face images, is created and saved on the centralized server, which helps to reduce memory load on the centralized server. It is noticed that the recognition accuracy is 100% for smaller size datasets and a little less accuracy for larger size datasets and also, results are compared with present methods to show the superiority of proposed method.

• Journal of Korea Technology Innovation Society
• /
• v.14 no.spc
• /
• pp.1285-1311
• /
• 2011

In this research, we investigated both present and potential entrepreneurs who are over 20 years old. The theme was that how businessmen's manners toward business and danger-perception have difference and are affected according to various factors. Besides, we also worked on the influence of manners toward enterprise and risk-perception variable on intention of starting and maintaining a business by using a decision-making model of consumers. The results are the followings. First, attitude toward enterprise was positive when the entrepreneur is man or unprofessional. This phenomenon was also observed if his or her parents had business foundation experience or he or she has self-realization motive rather than economical. Meanwhile, danger-recognition was high when the entrepreneur has no job, is more than 40 years old, has business background, or has affirmative enterprise attitude. Second, people who are man, have parents with business background or have self-realization motive on business foundation were more willing to start a business. Meanwhile, people who have affirmative enterprise manners, company with sales from 11 billion to 100 billion won or no business failure experience had high intention to maintain a business. Third, businessmen who are men, work in unprofessional job or have business experience had more strong desire to establish enterprise. Meantime, people who are old, have no jobs or have enterprise experience showed high danger-recognition level. At last, people who are men or jobless had strong will to start a business. So did the people who have positive attitude toward business or have parents who have business experience. Meantime, people with affirmative business manners or no experience of enterprise failure had strong intention to keep business.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.419-427
• /
• 2021

The purpose of this study is to identify the recognition and utilization of health information by acquisition channels for preliminary and elderly people. For the survey data of 200 people aged 55 to 64 and 200 seniors aged 65 or older, the chi-square test and Fisher's precision test were performed using MINITAB17. Although the two age groups were similar in obtaining health information through health professionals, preliminary elderly were more likely to obtain health information through mass media and Internet sites. In particular, the collection of health information through internet sites was more than four times higher than that of the elderly. While the preliminary people focused on searching the information on the health care and prevention, older people explored comprehensive information on health, including disease prevention and treatment, through each channel. Both groups showed positive recognition about the acquired health information. The results of this study confirmed that all channels, including internet sites, can be usefully used in the delivery of health-related information to the elderly in the future. In addition, it is suggested to consider age characteristics and health information utilized by each channel in the development of various contents for the improvement of self-health management of the elderly.

• Fashion & Textile Research Journal
• /
• v.5 no.4
• /
• pp.372-378
• /
• 2003

The purpose of this study is to compare the self consciousness of one's body cathexis with other people's. The sample subjects were 97 females between 18 and 24 years old. They were measured on November 1999 with the anthropometric measuring, and their front and side photographs were taken. First, we investigated the size recognition of 5 body parts and ready-made clothing, the consciousness of the size of 5 body parts and body proportion for subjects. Second, we organized panel group consisted of 30 females in twenties majoring the Clothing & Textiles. The consciousness of panel group to the subject's body proportion was investigated by using the front and side photographs of subjects, and was compared with self consciousness of subjects. Data were analyzed by frequency analysis and correlation analysis. Most of subjects recognized their status, bustgirth and waistgirth larger than their real size, but they recognized their hipgirth smaller than their real size and their weight similar to their real weight. And subjects were conscious of their status and bustgirth small, their weight, waistgith and hipgirth proper or a little big, and their body proportion normal or a little unbalanced. The self consciousness of one's body cathexis was related to heights of each part especially, and subjects had a tendency to appreciate their body proportion positively if they recognized themselves tall and thin. Upon comparison of the consciousness of subject's body between subjects themselves and panel group, the appreciation of panel group was better than those of subjects themselves. And we also certified the difference of consciousness of one's body cathexis between oneself and other people. The consciousness of other people was related to the size of each body part, but the self consciousness was predicted that it was more related to the psychological factor including satisfaction or preference.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.245-252
• /
• 2022

This study is significant in explaining the eSports awareness survey and future development direction of deaf people. Therefore, 189 deaf people were selected as the population, and the following conclusions were drawn by frequency analysis and t-test using SPSS 21.0 and Excel 2016. First, 67.7 percent of the 189 deaf people recognized eSports, 61.4 percent recognized it as a new sports system, and 65.6 percent participated directly or indirectly in eSports. Second, smartphones are the most common e-sports participating devices, and most of the participating events are Kartrider, which is recommended by friends. Third, the most inconvenient part of participating in eSports was the lack of eSports programs for deaf people, and the survey on whether to recommend eSports was the most likely. Fourth, the most common reason for not recognizing eSports as a new sport is that they are not actually sports, so they are not interested in participating. Fifth, there are statistically significant differences in eSports awareness, recognition and participation of deaf people by gender.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1187-1199
• /
• 2017

In recent years, research about Natural User Interface (NUI) has become focused because NUI system can give natural feelings for users in virtual reality. Most important thing in NUI system is how to communicate with the computer system. There are many things to interact with users such as speech, hand gestures, body actions. Among them, hand gesture is suitable for the purpose of NUI because people often use a relatively high frequency in daily life and hand gesture have meaning only by itself. This hand gestures called multi-cultural hand gesture and we proposed the method to recognize this kind of hand gestures. Proposed method is composed of Histogram of Oriented Gradients (HOG) used for hand shape recognition and Histogram of Oriented Displacements (HOD) used for hand center point trajectory recognition.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.762-766
• /
• 2002

This paper describes the emotion recognition algorithm using HMM(Hidden Markov Model) method. The relation between the mechanic system and the human has just been unilateral so far. This is the why people don't want to get familiar with multi-service robots of today. If the function of the emotion recognition is granted to the robot system, the concept of the mechanic part will be changed a lot. Pitch and Energy extracted from the human speech are good and important factors to classify the each emotion (neutral, happy, sad and angry etc.), which are called prosodic features. HMM is the powerful and effective theory among several methods to construct the statistical model with characteristic vector which is made up with the mixture of prosodic features

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.375.2-375
• /
• 2002

This paper describes the emotion recognition algorithm using HMM(Hidden Markov Model) method. The relation between the mechanic system and the human has just been unilateral so far This is the why people don't want to get familiar with multi-service robots. If the function of the emotion recognition is granted to the robot system, the concept of the mechanic part will be changed a lot. (omitted)

• Journal of Fisheries and Marine Sciences Education
• /
• v.26 no.4
• /
• pp.797-807
• /
• 2014

The purpose of this research is to clarify the influence of job satisfaction factors on the turnover of marine sports employees and propose the methodical and scientific preliminary data suggesting the development of marine sports and policy direction. To achieve this research was conducted on 247 marine sports workers from February to March, 2013 and the findings are shown below. Firstly, male workers showed higher satisfaction rate in social recognition and salary. Female workers showed higher satisfaction in work conditions. Married workers with related license holders negative in promotion, but workers who are 50 and older with high school diploma showed higher satisfaction. Secondly, group of singles showed higher satisfaction rate in social recognition and peer relationship. People with related majors showed higher satisfaction in suitability, salary, peer relationship and social recognition. Thirdly, those who show higher satisfaction in social recognition, work condition, salary, suitability, and promotion are show a lower likelihood of changing their job.