• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.227-232
• /
• 2003

Non-intrusive methods based on active remote IR illumination for eye tracking is important for many applications of vision-based man-machine interaction. One problem that has plagued those methods is their sensitivity to lighting condition change. This tends to significantly limit their scope of application. In this paper, we present a new real-time eye detection and tracking methodology that works under variable and realistic lighting conditions. eased on combining the bright-pupil effect resulted from IR light and the conventional appearance-based object recognition technique, our method can robustly track eyes when the pupils are not very bright due to significant external illumination interferences. The appearance model is incorporated in both eyes detection and tracking via the use of support vector machine and the mean shift tracking. Additional improvement is achieved from modifying the image acquisition apparatus including the illuminator and the camera.

• Journal of The Korean Association of Information Education
• /
• v.11 no.1
• /
• pp.99-114
• /
• 2007

The web-based discussion allows learners to participate in the learning actively and positively, and it can provide learners with the learner-oriented active interaction and learning environment. However, the web-based discussion produced communication-oriented learning environment using bulletin board and data directory and researched mainly the state and activation of the discussion, and had less system supporting dynamic discussion process. Even if the discussion made appearance partially and totally as learners' activities at a variety of web-based teaching, specific discussion-based teaching model was not developed. Therefore, a systematic web-based discussion system needs to be developed to activate human interaction and to give shape to the stages and elements of the discussion model. The paper supports dynamic discussion activities and applies Hill's common discussion model describing detailed discussion stages to develop systematic web-based discussion system.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1157-1160
• /
• 2005

The denoising and reconstruction of color images are increasingly studied in the field of computer vision and image processing. Especially, the denoising and reconstruction of color face images are more difficult than those of natural images because of the structural characteristics of human faces as well as the subtleties of color interactions. In this paper, we propose a denoising method based on PCA reconstruction for removing complex color noises on human faces, which is not easy to remove by using vectorial color filters. The proposed method is composed of the following five steps; training of canonical eigenface space using PCA, automatic extracting of face features using active appearance model, relighing of reconstructed color image using bilateral filter, extraction of noise regions using the variance of training data, and reconstruction using partial information of input images (except the noise regions) and blending of the reconstructed image with the original image. Experimental results show that the proposed denosing method efficiently removes complex color noises on input face images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.6
• /
• pp.1449-1462
• /
• 2013

We present a novel approach to producing facial caricature with Simpson cartoon style based on Moving Least Squares (MLS). We take advantage of employing the caricature stylization rule of caricature artist, Justin. Our method allows Simpson-style cartoon character similar to user's features by using Justin's technique, which is a set of caricature stylization rules. Our method transforms input photo image into Simpson style caricature by using MLS approximation. The unique characteristics of user in the photo can be detected by comparing to the mean face feature and the input face feature extracted by AAM(Active Appearance Model). To exaggerate the detected unique characteristics, we set up the exaggeration rules using Justin's technique. In addition, during the cartooning process, user's hairs and accessories are used to the deformed image to make a close resemblance. Our method preserves the reliable and stylized caricature through the exaggeration rules of the actual caricature artist's techniques. From this study, we can easily create a Simpson-style cartoon caricature to resemble user's features by combining a caricature with existing cartoon researches.

• Journal of Communications and Networks
• /
• v.13 no.4
• /
• pp.360-366
• /
• 2011

In this paper, we investigate the problem of power allocation in a heterogeneous network that is composed of a pair of cognitive users (CUs) and an infrastructure-based primary network. Since CUs have only limited effective spectrum-sensing ability and primary users (PUs) are not active all the time in all locations and licensed bands, we set up a new multi-area model to characterize the heterogeneous network. A novel combined interference-avoidance policy corresponding to different PU-appearance situations is introduced to protect the primary network from unacceptable disturbance and to increase the spectrum secondary-reuse efficiency. We use dual decomposition to transform the original power allocation problem into a two-layer optimization problem. We propose a low-complexity joint power-optimizing method to maximize the transmission rate between CUs, taking into account both the individual power-transmission constraints and the combined interference power constraint of the PUs. Numerical results show that for various values of the system parameters, the proposed joint optimization method with combined PU protection is significantly better than the opportunistic spectrum access mode and other heuristic approaches.

• Nutrition Research and Practice
• /
• v.3 no.1
• /
• pp.9-14
• /
• 2009

Aloe products are one of the top selling health-functional foods in Korea, however the adequate level of intake to achieve desirable effects are not well understood. The objective of this study was to determine the intestinal uptake and metabolism of physiologically active aloe components using in vitro intestinal absorption model. The Caco-2 cell monolayer and the everted gut sac were incubated with $5-50{\mu}M$ of aloin, aloe-emodin, and aloesin. The basolateral appearance of test compounds and their glucuronosyl or sulfated forms were quantified using HPLC. The % absorption of aloin, aloe-emodin, and aloesin was ranged from 5.51% to 6.60%, 6.60% to 11.32%, and 7.61% to 13.64%, respectively. Up to 18.15%, 18.18%, and 38.86% of aloin, aloe-emodin, and aloesin, respectively, was absorbed as glucuronidated or sulfated form. These results suggest that a significant amount is transformed during absorption. The absorption rate of test compounds except aloesin was similar in two models; more aloesin was absorbed in the everted gut sac than in the Caco-2 monolayer. These results provide information to establish adequate intake level of aloe supplements to maintain effective plasma level.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1337-1346
• /
• 2005

In this paper, we describe an algorithm which can automatically recognize human gesture for Human-Robot interaction. In early works, many systems for recognizing human gestures work under many restricted conditions. To eliminate these restrictions, we have proposed the method that can represent 3D and 2D gesture information simultaneously, APM. This method is less sensitive to noise or appearance characteristic. First, the feature vectors are extracted using APM. The next step is constructing a gesture space by analyzing the statistical information of training images with PCA. And then, input images are compared to the model and individually symbolized to one portion of the model space. In the last step, the symbolized images are recognized with HMM as one of model gestures. The experimental results indicate that the proposed algorithm is efficient on gesture recognition, and it is very convenient to apply to humanoid robot or intelligent interface systems.

• Journal of Korea Multimedia Society
• /
• v.5 no.3
• /
• pp.290-297
• /
• 2002

The appearance of web technology has accelerated the role of the application of multimedia technology, computer communication technology and multimedia application contents. Recently WBI model which is based on web has been proposed in the part of the new activity model of teaching-teaming. How to learn and evaluate is required to consider individual learner's learning level. And it is recognized that the needs of the efficient and automated education agents in the web-based instruction is increased But many education systems that had been studied recently did not service fluently the courses which learners had been wanting and could not provide the way for the learners to study the learning weakness which is observed in the continuous feedback of the course. In this paper we propose design of multi-module system for course scheduling of learner-oriented using weakness analysis algorithm. First proposed system monitors learner's behaviors constantly, evaluates them, and calculates his accomplishment and weakness. From this weakness the multi-agent prepares the learner a suitable course environment to strengthen his weakness. Then the learner achieves an active and complete teaming from the repeated and suitable course.

• Journal of Information Technology Services
• /
• v.16 no.2
• /
• pp.139-156
• /
• 2017

Since the global financial crisis of 2008, the continuous development and innovation in technology-related fields such as information and communications technology (ICT) are likely to swim against the recession. In this paradoxical situation, the necessity of financial innovation through ICT is on the rise. For this reason, the appearance of Fintech is more meaningful as a new converged industry with the potential to lead financial innovation. The term of Fintech is derived from combining 'Finance' and 'Technology.' In South Korea, one of the most popular types of Fintech is mobile payment. KakaoPay, which is the first mobile easy payment service in Korea, is a much more simplified type of mobile payment service than ones used in the past, and is provided by the most popular mobile messenger service in Korea, KakaoTalk. However, KakaoPay has few active users in spite of its many advantages, which include convenience, simplicity, and a powerful platform. Thus, the main purpose of this paper is to investigate influencing factors of user resistance on KakaoPay. In order to investigate specific factors, a research model is developed based on the unified understanding of user resistance put forth by Laumer and Eckhardt (2012). After gathering online survey data from KakaoTalk users, an empirical analysis is conducted to verify this research model. The results of this study give insights regarding user resistance factors in the Fintech sector, and by so doing, it is expected that the important factors of user resistance could help the diffusion of new services when new mobile payment services appear in the near future.