• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.67-75
• /
• 2006

Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance. Since it is difficult to generate realistic facial expressions by using only geometric deformations, detailed features such as textures should also be deformed to achieve more realistic expression. The existing methods such as the expression ratio image have drawbacks, in that detailed changes of complexion by lighting can not be generated properly. In this paper, we propose a nonlinear model for skin color change and a model-based synthesis method for facial expression that can apply realistic expression details under different lighting conditions. The proposed method is composed of the following three steps; automatic extraction of facial features using active appearance model and geometric deformation of expression using warping, generation of facial expression using a model for nonlinear skin color change, and synthesis of original face with generated expression using a blending ratio that is computed by the Euclidean distance transform. Experimental results show that the proposed method generate realistic facial expressions under various lighting conditions.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.2
• /
• pp.47-54
• /
• 2007

This paper proposes a user interface based on video see-through environment which shows the images via stereo-cameras so that the user can control the computer systems or other various processes easily. We include an AR technology to synthesize virtual buttons; the graphic images are overlaid on the captured frames taken by the camera real-time. We search for the hand position in the frames to judge whether or not the user selects the button. The result of judgment is visualized through changing of the button color. The user can easily interact with the system by selecting the virtual button in the screen with watching the screen and moving her fingers at the air.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.2
• /
• pp.135-141
• /
• 2004

This paper proposes a new heuristic search technique for obstacle avoidance of autonomous underwater vehicles equipped with a looking ahead obstacle avoidance sonar. We suggest the fuzzy relation between the sonar sections and the properties of real world environment. Bandler and Kohout's fuzzy relational method are used as the mathematical implementation for the analysis and synthesis of relations between the partitioned sections of sonar over the real-world environmental properties. The direction of the section with optimal characteristics would be selected as the successive heading of AUVs for obstacle avoidance. For the technique using in this paper, sonar range must be partitioned into multi equal sections; membership functions of the properties and the corresponding fuzzy rule bases are estimated heuristically. With the two properties Safety, Remoteness and sonar range partitioned in seven sections, this study gives the good result that enables AUVs to navigate through obstacles in the optimal way to goal.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.2
• /
• pp.166-178
• /
• 2000

As the 21st century signifies an information-oriented society, the computer integration takes place in all walks of human presence. Needs for computer and network-integrated automation present new challenges in military as well as commercial facility systems engineering. Since the first intelligent building appeared in USA in 1984, it gradually became an essential capability for the building industry requirement these days. Intelligent Building System(IBS) is evolving to be very complex because there are many subsystems such as telecommunication(TC), office automation(OA), building automation(BA), security, construction environments, etc. During the planing phase of IBS development, therefore, a disciplined systems engineering must be performed to analyze stake- holder's requirements to build an optimized system while minimizing trial-and-error expenses and risks. This paper presents a conceptual design of BAS applying systems engineering methods. The contribution of this study includes the development of IBS subsystem specification for building automation subsystem, which is a part of IBS, using the methodology of requirement analysis, functional analysis, synthesis, and verification. A computer-aided systems engineering s/w, RDD-100, was used to improve the system design efficiency and to promote the product design knowledge management for reuse in later design programs.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.22-30
• /
• 2019

For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot's understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.79-87
• /
• 2021

In recent years research on automatic font generation with machine learning mainly focus on using transformation-based methods, in comparison, generative model-based methods of font generation have received less attention. Transformation-based methods learn a mapping of the transformations from an existing input to a target. This makes them ambiguous because in some cases a single input reference may correspond to multiple possible outputs. In this work, we focus on font generation using the generative model-based methods which learn the buildup of the characters from noise-to-image. We propose a novel way to train a conditional generative deep neural model so that we can achieve font style control on the generated font images. Our research demonstrates how to generate new font images conditioned on both character class labels and character style labels when using the generative model-based methods. We achieve this by introducing a modified generator network which is given inputs noise, character class, and style, which help us to calculate losses separately for the character class labels and character style labels. We show that adding the character style vector on top of the character class vector separately gives the model rich information about the font and enables us to explicitly specify not only the character class but also the character style that we want the model to generate.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.85-94
• /
• 2023

Image halftoning is a technique for varying grayscale images into two-tone binary images. Unfortunately, the static representation of an image-half toning, wherever each pixel intensity is combined by its local neighbors only, causes missing subjective problem. Also, the existing noise causes an instability criterion. In this paper an image half-toning is represented as a dynamical system for recognizing the global representation. Also, noise is reduced based on a probabilistic model. Since image half-toning is considered as 2-D matrix with a full connected pass, this structure is recognized by the dynamical system of Cellular Neural Networks (CNNs) which is defined by its template. Bayesian Rough Sets is used in exploiting the ideal CNNs construction that synthesis its dynamic. Also, Bayesian rough sets contribute to enhance the quality of the halftone image by removing noise and discovering the effective parameters in the CNNs template. The novelty of this method lies in finding a probabilistic based technique to discover the term of CNNs template and define new learning rules for CNNs internal work. A numerical experiment is conducted on image half-toning corrupted by Gaussian noise.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.494-496
• /
• 2021

최근 경량 딥러닝 기반 키워드 음성인식은 가전, 완구, 키오스크 등 다양한 응용에 음성 인터페이스를 쉽게 적용할 수 있는 기술로서 주목받고 있다. 키워드 음성인식은 일부 키워드만 인식 가능한 음성인식 기술로서 저성능 디바이스에서 활용 가능한 장점이 있다. 그러나 응용에 따라 필요한 키워드에 대하여 다시 음성데이터를 수집해야하고 이를 학습하여 모델을 새로 준비해야하는 단점이 있다. 따라서 본 연구에서는 음성데이터 수집 없이 음성합성을 통해 생성한 음성으로만 키워드 음성인식 모델을 학습하는 음성합성 기반 자동 학습 기법을 제안하였다. 생성한 음성데이터를 활용하고자하는 시도가 활발히 이루어지고 있으나, 기존 연구에서는 정확도를 유지하기 위하여 수집한 실제 음성데이터가 필요한 한계가 있다. 제안한 자동 학습 기법은 생성한 음성데이터에 대해 복합 데이터 증대 기법을 적용하여 실제 음성데이터 없이 키워드 음성인식의 정확도를 높였다. 제안한 기법에 대하여 상용 음성합성 서비스를 기반으로 수집한 한국어 키워드 데이터세트를 활용하여 성능평가를 진행하였다. 20개 한국어 키워드에 대해 실험한 결과, 제안한 기법을 적용하여 학습시킨 키워드 음성인식 모델의 정확도는 86.44%임을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.11-14
• /
• 2020

The importance of data in the development of deep learning is very high. Data with high morphological features are usually utilized in the domains where careful lens calibrations are needed by a human to capture those data. Synthesis of high morphological data for that domain can be a great asset to improve the classification accuracy of systems in the field. Unsupervised learning can be employed for this task. Generating photo-realistic objects of interest has been massively studied after Generative Adversarial Network (GAN) was introduced. In this paper, we propose Morpho-GAN, a method that unifies several GAN techniques to generate quality data of high morphology. Our method introduces a new suitable training objective in the discriminator of GAN to synthesize images that follow the distribution of the original dataset. The results demonstrate that the proposed method can generate plausible data as good as other modern baseline models while taking a less complex during training.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.37-50
• /
• 2023

In general, PLL or DDS are mainly used as precise and stable frequency synthesis methods. For stable operation, a PWM frequency generation algorithm was designed and implemented using FPGA. This is an algorithm that creates a frequency 8,192 times the target frequency and then performs the D flip-flop 13 times to generate multiple frequencies with a precision of 1 Hz. Using the designed algorithm, it is applied to the Berthing system for stopping trains in station. The applied product was developed and tested against the existing operating system to confirm its superior performance in terms of frequency generation accuracy.