• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.333-336
• /
• 2007

본 논문에서는 감정인식 분야에서 가장 많이 사용되어지는 음성신호와 얼굴영상을 가지고 4개의(기쁨, 슬픔, 화남, 놀람) 감정으로 인식하고 각각 얻어진 감정인식 결과를 Multi modal 기법을 이용해서 이들의 감정을 융합한다. 이를 위해 얼굴영상을 이용한 감정인식에서는 주성분 분석(Principal Component Analysis)법을 이용해 특징벡터를 추출하고, 음성신호는 언어적 특성을 배재한 acoustic feature를 사용하였으며 이와 같이 추출된 특징들을 각각 신경망에 적용시켜 감정별로 패턴을 분류하였고, 인식된 결과는 감정표현 시스템에 작용하여 감정을 표현하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.130-133
• /
• 2003

The robot has recently emerged as a factor in the daily lives of humans, taking the form of a mechanical pet or similar source of entertainment. A robot system that is designed to co-exist with humans, i.e., a coexistence-type robot system, is important to be "it exists in various environments with the person, and robot system by which the interaction of a physical, informational emotion with the person etc. was valued". When studying the impact of intimacy in the human/robot relationship, we have to examine the problems that can arise as a result of physical intimacy(coordination on safety in the hardware side and a soft side). Furthermore, We should also consider the informational aspects of intimacy (recognition technology, and information transport and sharing). This paper reports the interim results of the research of a system configuration that enhances the physical intimacy relationship in the symbiosis of the human and the robot.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.16-18
• /
• 2017

최근 딥 러닝의 발전으로 얼굴인식뿐만 아니라 더 세부적인 기술인 ID식별, 감정인식 등을 분류할 수 있는 알고리즘이 많이 제안되었다. 하지만 딥 러닝은 방대한 연산량을 처리해야 하기 때문에 실시간으로 영상을 구현하는 것은 한계가 있다. 본 논문은 위와 같은 문제를 개선하기 위하여 얼굴인식은 연산량이 비교적 적은 HOG알고리즘을 적용하여 전처리를 진행한다. 그 이후 ID식별 네트워크인 FaceNet과 EmotiW 2017 Challenge의 논문의 감정인식 네트워크를 Multi-Thread 기술을 적용하여 스레드를 분할 연산을 통하여 실시간으로 영상을 출력하는 알고리즘을 제안한다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.35 no.2 s.121
• /
• pp.81-90
• /
• 2007

This study used the functions for public benefits as a standard for evaluating Green Tourism. By referring to the existing literature, the "function of building emotion", the "function of providing a natural environment", the "function of preserving traditional cultures", and the "function of maintaining the local community" have been selected as the measuring variables. Detailed sub-variables of each function were prepared to examine and analyze the recognition of these are the part of Green Tourists. The Green Tourists of Yangsuri in Yangpyeong, Sinnonri in Yangpyeong, and Jurokri in Yeoju participated in the survey for which 13 variables were used as measurement. The results are as follows: First, Green Tourists recognize farm villages as places for rest and relaxation and they laid great importance on the function of providing access to the natural environment. Secondly, out of the 13 measurement variables, "beautiful scenery in farm village", "making a contribution to village income", and "trust in agricultural products" greatly influenced the overall evaluation of Green Tourism. Thirdly, regarding the relationship between the functions for public benefits and Green Tourism, it was found that "facilities and activities for experiencing farming", "facilities for rest", and "beautiful scenery in farm villages" are closely related to building the emotion experienced in these villages, and that "cultivating environmentally-friendly agricultural products" and "beautiful scenery in farm village" are closely related to the function of providing access to the natural environment.

• Journal of Fashion Business
• /
• v.6 no.3
• /
• pp.94-109
• /
• 2002

The advent of the information age, advancement of the multi-media, and proliferation of internet are all ushering-in a new era of a cyber world. The artistic expression is unfolding into a new genre of a new era.. In the modern art, the boundary between the fine art and the applied art is becoming blurred, and further, distinction of fine art from popular art is also becoming meaningless. The advancement of science and technology, by offering new materials and visual forms, is contributing to the expansion of the morden art's horizon. As fashion illustration is gaining recognition as a form of art which mirrors today's realities, it has also become increasingly necessary to add variety and newness. Fashion illustration is thus becoming the visual language of the modern world, capable of conveying artistic emotion, and at the same time able to effectively communicate the image of fashion to the masses. The increasing awareness of artistic talent and ingenuity as essential components of fashion illustration is yielding greater fusion between fashion illustration and art & technology. This has resulted in the use of the advanced computer technology as a tool for crafting artistic expressions, such as fashion illustration, and this new tool has opened-up new possibilities for expressing images and colors. Further, the computer-aided fashion illustration is emerging as a new technique for expression. The concept of fashion illustration, history of fashion illustration from its incepton to modern date is reviewed and the simplicity has been researched throughout past studies published in Korean and overseas Journals.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.157-163
• /
• 2014

User's sensitivity is recognized as a very important parameter for communication between company, government and personnel. Especially in many studies, researchers use voice tone, voice speed, facial expression, moving direction and speed of body, and gestures to recognize the sensitivity. Multiplex modality is more precise than single modality however it has limited recognition rate and overload of data processing according to multi-sensing also an excellent algorithm is needed to deduce the sensing value. That is as each modality has different concept and property, errors might be happened to convert the human sensibility to standard values. To deal with this matter, the sensibility expression modality is needed to be extracted using technologies like analyzing of relational network, understanding of context and digital filter from multiplex modality. In specific situation to recognize the sensibility if the priority modality and other surrounding modalities are processed to implicit values, a robust system can be composed in comparison to the consuming of computer resource. As a result of this paper, it is proposed how to assign the weight of multiplex modality using implicit data.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.355-362
• /
• 2010

Face tracking is to estimate the motion of a non-rigid face together with a rigid head in 3D, and plays important roles in higher levels such as face/facial expression/emotion recognition. In this paper, we propose an AAM-based face tracking algorithm. AAM has been widely used to segment and track deformable objects, but there are still many difficulties. Particularly, it often tends to diverge or converge into local minima when a target object is self-occluded, partially or completely occluded. To address this problem, we utilize the scale invariant feature transform (SIFT). SIFT is an effective method for self and partial occlusion because it is able to find correspondence between feature points under partial loss. And it enables an AAM to continue to track without re-initialization in complete occlusions thanks to the good performance of global matching. We also register and use the SIFT features extracted from multi-view face images during tracking to effectively track a face across large pose changes. Our proposed algorithm is validated by comparing other algorithms under the above 3 kinds of occlusions.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• Science of Emotion and Sensibility
• /
• v.23 no.1
• /
• pp.29-40
• /
• 2020

Visually impaired people use tactile maps to get spatial information about their surrounding environment, find their way, and improve their independent mobility. However, classical tactile maps that make use of braille to describe the location within the map have several limitations, such as the lack of information due to constraints on space and limited feedback possibilities. This study describes the development of a new multi-modal interactive tactile map interface that addresses the challenges of tactile maps to improve the usability and independence of visually impaired people when using tactile maps. This interface adds touch gesture recognition to the surface of tactile maps and enables the users to verbally interact with a voice agent to receive feedback and information about navigation routes and points of interest. A low-cost prototype was developed to conduct usability tests that evaluated the interface through a survey and interview given to blind participants after using the prototype. The test results show that this interactive tactile map prototype provides improved usability for people over traditional tactile maps that use braille only. Participants reported that it was easier to find the starting point and points of interest they wished to navigate to with the prototype. Also, it improved self-reported independence and confidence compared with traditional tactile maps. Future work includes further development of the mobility solution based on the feedback received and an extensive quantitative study.

• Journal of Ethics
• /
• no.84
• /
• pp.217-242
• /
• 2012

This essay aims to explore the importance of ethics education in Korean multicultural society. In 2011, it is reported by the Ministry of Education, Science and Technology that the final goal of Korean multicultural ethics education is to establish the foundations of National identity and of moral values in general. It might be a ideological tool, however, that can suppress the minority in Korea. In that sense, an orientation of ethics education in Korean multicultural society is basically to consider all moral agents in ethics. To give any solution, therefore, an attention will be paid to the notions of emotion and the likeness of moral fibre. Most important is that we have certain emotions which are in society beyond individual feelings. It is the only ethical subject and existence who we can have them. In that point, having them enables us to make any decision on the ground of moral values. By the quality of the likeness of moral fibre, furthermore, we can recognize and exercise moral values together without any difference in multicultural society. This makes sense of an identity as a Korean. Therefore, having emotions is helpful in taking the moral foundations of Korean multicultural society and the self-recognition of a Korean in the sense of the likeness of moral fibre give an ethical direction to us, the Korean multicultural society of ethical culture in the future.