• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.10-17
• /
• 2017

This study is the first attempt to raise face recognition ability through machine learning algorithm and apply to CRM's information gathering, analysis and application. In other words, through face recognition of VIP customer in distribution field, we can proceed more prompt and subdivided customized services. The interest in machine learning, which is used to implement artificial intelligence, has increased, and it has become an age to automate it by using machine learning beyond the way that a person directly models an object recognition process. Among them, Deep Learning is evaluated as an advanced technology that shows amazing performance in various fields, and is applied to various fields of image recognition. Face recognition, which is widely used in real life, has been developed to recognize criminals' faces and catch criminals. In this study, two image analysis models, TF-SLIM and Inception-V3, which are likely to be used for criminal face recognition, were selected, analyzed, and implemented. As an evaluation criterion, the image recognition model was evaluated based on the accuracy of the face recognition program which is already being commercialized. In this experiment, it was evaluated that the recognition accuracy was good when the accuracy of the image classification was more than 90%. A limit of our study which is a way to raise face recognition is left as a further research subjects.

• Korean Journal of Health Education and Promotion
• /
• v.24 no.4
• /
• pp.161-179
• /
• 2007

To commonly apply the ${\ulcorner}$Measurement parameter for housewives for rearing-related supports of a husband${\lrcorner}$ in Korea and Japan, the current study conducted to confirm the relationship between recognition of a housewife for rearing-related supports of a husband and mental health after reviewing the appropriateness of the parameter. For the statistical analysis, 829 married Korean women in D city and 1,302 Japanese women in S city having children before entering a school were subjected for the study. For reviewing the appropriateness of the parameter, the simultaneous factor analysis that adopted the structural equation modeling was used. As the result of the analysis, 10 categories of factor structural model comprising the ${\ulcorner}$Recognition of a housewife for rearing-related supports of a husband${\lrcorner}$ resulted with the secondary model which sets of ${\ulcorner}$Recognition for emotional support${\lrcorner}$, ${\ulcorner}$Recognition for instrumental support${\lrcorner}$ and ${\ulcorner}$Recognition for information support${\lrcorner}$ as the primary factor and ${\ulcorner}$Recognition of a housewife for rearing-related supports of a husband${\lrcorner}$ as the secondary factor, and the model was found to be appropriate for the data in Korea and Japan. The result is considered to prove the constructs validity of ${\ulcorner}$Recognition of a housewife for rearing-related supports of a husband${\lrcorner}$ parameter. In addition, the relationship between ${\ulcorner}$Recognition of a housewife for rearing-related supports of a husband${\lrcorner}$ and mental health(GHQ) was reviewed by using multiple indicator model, and found the similarity of Korean and Japanese data. The scores measured by using the above parameter resulted to show high relationship with educational level of housewife, family configuration, and number of children.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1485-1490
• /
• 2004

Recently, we have remarkable developments in intelligent robot systems. The remarkable features of intelligent robot are that it can track user, does face recognition and vital for many surveillance based systems. Advantage of face recognition when compared with other biometrics recognition is that coerciveness and contact that usually exist when we acquire characteristics do not exist in face recognition. However, the accuracy of face recognition is lower than other biometric recognition due to decrease in dimension from of image acquisition step and various changes associated with face pose and background. Factors that deteriorate performance of face recognition are many such as distance from camera to face, lighting change, pose change, and change of facial expression. In this paper, we implement a new 3D active camera system to prevent various pose variation that influence face recognition performance and propose face recognition algorithm for intelligent surveillance system and mobile robot system.

• The Journal of the Korea Contents Association
• /
• v.16 no.1
• /
• pp.585-594
• /
• 2016

This study is aimed at researching and analyzing the students' recognition and practice of the patents medical information, who are majoring in medical records and will be working as medical records technician, letting them recognize the importance of information, and at offering basic data required for development of medical records curriculum and for establishment of medical records protection policy. This study was conducted from 18th May through 6th June 2015, targeting 340 students enrolled four universities, by t-test, variance analysis, Pearson correlation analysis and multiple regression analysis. As a result of this study, the point of protection recognition and practice recognition is 3.55 and 3.49, respectively, out of 5. With regard to recognition of medical information protection, there was a significant difference in grade, satisfaction for major, experience of medical information protection education and recognition of law, while for recognition of practice, in grade, satisfaction for major, educational experience and damage of medical information exposure. Recognition of protection and recognition of practice had a significant static correlation, and recognition of information exposure, recognition of social issue and recognition of legal system had significant positive effect on recognition of practice. In order to raise the recognition of protection and recognition of practice, based on this study, it is considered necessary for the universities to educate the damage of medical information exposure and importance of medical records management, and to raise the students' recognition.

• 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.

• International Journal of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.39-47
• /
• 2016

This study is a smart tourism research based on face recognition applied system that manages individual information of foreign tourists to smartphone. It is a way to authenticate by using face recognition, which is biometric information, as a technology applied to identification inquiry, immigration control, etc. and it is designed so that tourism companies can provide customized service to customers by applying algorism to smartphone. The smart tourism system based on face recognition is a system that prepares the reception service by sending the information to smartphone of tourist service company guide in real time after taking faces of foreign tourists who enter Korea for the first time with glasses attached to the camera. The smart tourism based on face recognition is personal information recognition technology, speech recognition technology, sensing technology, artificial intelligence personal information recognition technology, etc. Especially, artificial intelligence personal information recognition technology is a system that enables the tourism service company to implement the self-promotion function to commemorate the visit of foreign tourists and that enables tourists to participate in events and experience them directly. Since the application of smart tourism based on face recognition can utilize unique facial data and image features, it can be beneficially utilized for service companies that require accurate user authentication and service companies that prioritize security. However, in terms of sharing information by government organizations and private companies, preemptive measures such as the introduction of security systems should be taken.

• The Korean Journal of Ecology
• /
• v.25 no.6
• /
• pp.365-369
• /
• 2002

We had 18 eggs artificially hatched in a mass breeding place of black-tailed gulls and examined the individual recognition between young siblings in a laboratory environment. The results of the experiment showed that the young gulls selectively responded to their siblings and non-siblings at an early stage after hatching. It was shown that they began to recognize the begging call among the voice signals of siblings and non-siblings 15-16 days after hatching, and the chirirah call 11-12 days after hatching. Also, more significant results were shown with the chirirah call than with the begging call. In an experiment of visual recognition between siblings and non-siblings, the young black-tailed gulls approached their siblings significantly 9-10 days after hatching. The recognition between young siblings in a mass breeding place provides an important evolutionary indicator in terms of their social behaviors.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.23-31
• /
• 2002

In this paper we propose a new feature vector for recognition of the facial expression based on Gibbs distributions which are well suited for representing the spatial continuity. The extracted feature vectors are invariant under translation rotation, and scale of an facial expression imege. The Algorithm for recognition of a facial expression contains two parts： the extraction of feature vector and the recognition process. The extraction of feature vector are comprised of modified 2-D conditional moments based on estimated Gibbs distribution for an facial image. In the facial expression recognition phase, we use discrete left-right HMM which is widely used in pattern recognition. In order to evaluate the performance of the proposed scheme, experiments for recognition of four universal expression (anger, fear, happiness, surprise) was conducted with facial image sequences on Workstation. Experiment results reveal that the proposed scheme has high recognition rate over 95%.

• The Journal of the Korea Contents Association
• /
• v.13 no.9
• /
• pp.10-19
• /
• 2013

This Paper proposed the development of new magnetic sensor and recognition system to expendite pattern recognition of a handwriting character. Received character graphics should be performed the session and balancing and no extraction of end points, bend points and juntions separately. The Artifical intelligence algorithm is adapted to structure snalysis and recognition process by individual basic letter dictionary except for the handwriing character graphic dictionaryimproving error of recognition algorithm and enomous dictionary for generalization. In this Paper, recognition rate of the received character are compared with pre registered character at letter dictionary for performance test of magnetic ball sensor. As a result of unicode conversion and eomparison, the artificial intelligence study have recognition rate more than 95% at initial recognition rate of 70%.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.515-522
• /
• 2021

It is hard to prepare sufficient training data for speech emotion recognition due to the difficulty of emotion labeling. In this paper, we apply transfer learning with large-scale training data for speech recognition on a transformer-based model to improve the performance of speech emotion recognition. In addition, we propose a method to utilize context information without decoding by multi-task learning with speech recognition. According to the speech emotion recognition experiments using the IEMOCAP dataset, our model achieves a weighted accuracy of 70.6 % and an unweighted accuracy of 71.6 %, which shows that the proposed method is effective in improving the performance of speech emotion recognition.