• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.103-108
• /
• 2012

Recently, as the prevalence of high-performance mobile devices and the application of the multimedia content are expanded, Super Resolution (SR) technique which reconstructs low resolution images to high resolution images is becoming important. And in the mobile devices, the development of the SR algorithm considering the operation quantity or memory is required because of using the restricted resources. In this paper, we propose a new single frame fast SR technique suitable for mobile devices. In order to prevent color distortion, we change RGB color domain to HSV color domain and process the brightness information V (Value) considering the characteristics of human visual perception. First, the low resolution image is enlarged by the improved fast back projection considering the noise elimination. And at the same time, the reliable edge map is extracted by using the LoG (Laplacian of Gaussian) filtering. Finally, the high definition picture is reconstructed by using the edge information and the improved back projection result. The proposed technique removes effectually the unnatural artefact which is generated during the super resolution restoration, and the edge information which can be lost is amended and emphasized. The experimental results indicate that the proposed algorithm provides better performance than conventional back projection and interpolation methods.

• The Journal of Korean Academy of Prosthodontics
• /
• v.60 no.2
• /
• pp.222-230
• /
• 2022

Digital technology is gradually expanding its field and has a great influence on various fields of dentistry. Recently in digital dentistry, the importance of superimposing various 3-dimensional (3D) image data is emerging, in order to utilize gathered data effectively for diagnosis and prosthesis fabrication. Integrating data from facial scans, intraoral scans, and mandibular movement recordings can create a virtual patient. A virtual patient is formed by integrating digital 3D diagnostic data such as intraoral and extraoral soft tissues, residual dentition, and dynamic occlusion, and the results of prosthetic treatment can be evaluated virtually. The patients in this case report were a 37-year-old female whose chief complaint is that the appearance of the existing prosthesis was distorted and a 55-year-old female patient whose anterior prosthesis needed to be refabricated after the endodontic treatment. 3D facial scans were obtained from each patient, and the patient's mandibular movements were recorded using ARCUS Digma 2 (KaVo Dental GmbH, Biberach an der Riss, Germany). The collected data were integrated on computer-aided design (CAD) software (Exocad dental CAD; exocad GmbH, Darmstadt, Germany) and transferred to a virtual articulator to create a digital virtual patient. The temporary fixed prostheses were designed, restored, and evaluated, and it was reflected into the final restorations. With the aid of the virtual dental patient, accuracy and predictability could be increased throughout treatment, simplifying the occlusal adjustment and clinical evaluation with improved esthetic outcomes.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1021-1028
• /
• 2005

The general solution for classification and regression problems can be found by matching and modifying matrices with the information in real world and then these matrices are teaming in neural networks. This paper treats primary space as a real world, and dual space that Primary space matches matrices using kernel. In practical study, there are two kinds of problems, complete system which can get an answer using inverse matrix and ill-posed system or singular system which cannot get an answer directly from inverse of the given matrix. Further more the problems are often given by the latter condition; therefore, it is necessary to find regularization parameter to change ill-posed or singular problems into complete system. This paper compares each performance under both classification and regression problems among GCV, L-Curve, which are well known for getting regularization parameter, and kernel methods. Both GCV and L-Curve have excellent performance to get regularization parameters, and the performances are similar although they show little bit different results from the different condition of problems. However, these methods are two-step solution because both have to calculate the regularization parameters to solve given problems, and then those problems can be applied to other solving methods. Compared with UV and L-Curve, kernel methods are one-step solution which is simultaneously teaming a regularization parameter within the teaming process of pattern weights. This paper also suggests dynamic momentum which is leaning under the limited proportional condition between learning epoch and the performance of given problems to increase performance and precision for regularization. Finally, this paper shows the results that suggested solution can get better or equivalent results compared with GCV and L-Curve through the experiments using Iris data which are used to consider standard data in classification, Gaussian data which are typical data for singular system, and Shaw data which is an one-dimension image restoration problems.

• The Journal of Korean Academy of Prosthodontics
• /
• v.59 no.4
• /
• pp.487-496
• /
• 2021

Full mouth rehabilitation is re-organizing the occlusion of the remaining teeth and missing teeth considering the functions, esthetics, and neuromuscular harmony. With the loss of multiple teeth, the patient's occlusal plane gradually collapses and the vertical dimension can be reduced. Since reduced vertical dimension can be a potential etiology of the temporomandibular joint and masticatory muscles, prosthetic restoration with increased vertical dimension is required. This case report is about a 68 years old patient with vertical dimension loss due to worn dentition and multiple loss of teeth. In this case, the loss of vertical dimension is assessed carefully using the digital dentistry technology. Using CAD software in digital analysis step, the occlusal plane was established and evaluated using several criteria. Orienting the position of the bone and teeth using CBCT image, patient's condition was visualized in 3 dimension and treatment planning was possible virtually. The information that matches the patient's condylar position with the articulator, which is the virtual face bow, is reproduced on the actual articulator, and evaluated again. After the evaluation, provisional prosthesis was fabricated and it was confirmed that the patient adapts without any abnormality. This was implemented as a final prosthesis. As a result, the patient obtained satisfying results, utilizing the benefits of digital dentistry technology and traditional methods.