• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.41-68
• /
• 2019

Multi-view learning considers data from various viewpoints as well as attempts to integrate various information from data. Multi-view learning has been studied recently and has showed superior performance to a model learned from only a single view. With the introduction of deep learning techniques to a multi-view learning approach, it has showed good results in various fields such as image, text, voice, and video. In this study, we introduce how multi-view learning methods solve various problems faced in human behavior recognition, medical areas, information retrieval and facial expression recognition. In addition, we review data integration principles of multi-view learning methods by classifying traditional multi-view learning methods into data integration, classifiers integration, and representation integration. Finally, we examine how CNN, RNN, RBM, Autoencoder, and GAN, which are commonly used among various deep learning methods, are applied to multi-view learning algorithms. We categorize CNN and RNN-based learning methods as supervised learning, and RBM, Autoencoder, and GAN-based learning methods as unsupervised learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.115-121
• /
• 2020

With the spread of IoT technology, various IoT applications using facial recognition are emerging. This paper describes the design and implementation of a remote control system using deep learning-based face recognition and hand gesture recognition. In general, an application system using face recognition consists of a part that takes an image in real time from a camera, a part that recognizes a face from the image, and a part that utilizes the recognized result. Raspberry PI, a single board computer that can be mounted anywhere, has been used to shoot images in real time, and face recognition software has been developed using tensorflow's FaceNet model for server computers and hand gesture recognition software using OpenCV. We classified users into three groups: Known users, Danger users, and Unknown users, and designed and implemented an application that opens automatic door locks only for Known users who have passed both face recognition and hand gestures.

• Imaging Science in Dentistry
• /
• v.51 no.1
• /
• pp.17-25
• /
• 2021

Purpose: This study was performed to investigate mandibular canal displacement in patients with ameloblastoma using a 3-dimensional mirrored-model analysis. Materials and Methods: The sample consisted of computed tomographic scans of patients with ameloblastoma (n=10) and healthy controls (n=20). The amount of mandibular canal asymmetry was recorded as a continuous variable, while the buccolingual (yaw) and supero-inferior (pitch) directions of displacement were classified as categorical variables. The t-test for independent samples and the Fisher exact test were used to compare groups in terms of differences between sides and the presence of asymmetric inclinations, respectively (P<0.05). Results: The length of the mandibular canal was similar on both sides in both groups. The ameloblastoma group presented more lateral (2.40±4.16 mm) and inferior (-1.97±1.92 mm) positions of the mental foramen, and a more buccal (1.09±2.75 mm) position of the middle canal point on the lesion side. Displacement of the mandibular canal tended to be found in the anterior region in patients with ameloblastoma, occurring toward the buccal and inferior directions in 60% and 70% of ameloblastoma patients, respectively. Conclusion: Mandibular canal displacement due to ameloblastoma could be detected by this superimposed mirrored method, and displacement was more prevalent toward the inferior and buccal directions. This displacement affected the mental foramen position, but did not lead to a change in the length of the mandibular canal. The control group presented no mandibular canal displacement.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.239-246
• /
• 2021

In the field of computer graphics and HCI, there are many studies on systems that create characters and interact naturally. Such studies have focused on the user's response to the user's behavior, and the study of the character's behavior to elicit positive emotions from the user remains a difficult problem. In this paper, we develop a prototype of an interaction system to elicit positive emotions from users according to the movement of virtual characters using artificial intelligence technology. The proposed system is divided into face recognition and motion generation of a virtual character. A depth camera is used for face recognition, and the recognized data is transferred to motion generation. We use imitation learning as a learning model. In motion generation, random actions are performed according to the first user's facial expression data, and actions that the user can elicit positive emotions are learned through continuous imitation learning.

• The korean journal of orthodontics
• /
• v.52 no.3
• /
• pp.172-181
• /
• 2022

Objective: The objectives of this study were to compare the time-dependent changes in occlusal contact area (OCA) and bite force (BF) of the deviated and non-deviated sides in mandibular prognathic patients with mandibular asymmetry before and after orthognathic surgery and investigate the factors associated with the changes in OCA and BF on each side. Methods: The sample consisted of 67 patients (33 men and 34 women; age range 15-36 years) with facial asymmetry who underwent 2-jaw orthognathic surgery. OCA and BF were taken before presurgical orthodontic treatment, within 1 month before surgery, and 1 month, 3 months, 6 months, 1 year, and 2 years after surgery. OCA and BF were measured using the Dental Prescale System. Results: The OCA and BF decreased gradually before surgery and increased after surgery on both sides. The OCA and BF were significantly greater on the deviated side than on the non-deviated side before surgery, and there was no difference after surgery. According to the linear mixed-effect model, only the changes in the mandibular plane angle had a significant effect on BF (p < 0.05). Conclusions: There was a difference in the amount of the OCA and BF between the deviated and non-deviated sides before surgery. The change in mandibular plane angle affects the change, especially on the non-deviated side, during the observation period.

• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1481-1491
• /
• 2021

Since most biosignals rely on contact-based measurement, there is still a problem in that it is hard to provide convenience to users by applying them to daily life. In this paper, we present a mobile application for estimating heart rate based on a deep learning model. The proposed application measures heart rate by capturing real-time face images in a non-contact manner. We trained a three-dimensional convolutional neural network to predict photoplethysmography (PPG) from face images. The face images used for training were taken in various movements and situations. To evaluate the performance of the proposed system, we used a pulse oximeter to measure a ground truth PPG. As a result, the deviation of the calculated root means square error between the heart rate from remote PPG measured by the proposed system and the heart rate from the ground truth was about 1.14, showing no significant difference. Our findings suggest that heart rate measurement by mobile applications is accurate enough to help manage health during daily life.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1115-1126
• /
• 2021

In this paper, we developed a mobile student ID providing a self sovereignty identity (SSI) which replaces the conventional plastic-type student ID that includes private information of a student such as a name, a student number, a facial photo, etc. The implemented mobile student ID solves the problem of exposing student's identity due to a loss or a theft of a plastic-type student ID, and it has a structure and process of FRANCHISE model which is developed by a concept of a decentralized Identity(DID) of a Blockchain, in which specialized for convenience as an electronic student ID through an application on a smart phone device. In addition, it protects student's privacy by controlling personal information on oneself. By using a smartphone, not only it easily identifies the student but also it expands to several services such as participation in school events, online authentication, and a student's exchange program among colleges.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.2
• /
• pp.234-240
• /
• 2022

Floating-Harbor syndrome (FHS) is a rare genetic disorder. This report introduced in a patient with FHS. Distinctive facial characteristics, severe skeletal class 3 malocclusion with underdeveloped maxilla and protruded mandible, congenital missing teeth, microdontia and ectopic positions of maxillary teeth were presented in the patient. In his twin sister, mild skeletal class 3 malocclusion with protruded mandible was observed but congenital missing teeth and microdontia were not observed. High-arched palate, narrow V-shaped maxillary arch compared to wide and ovoid mandibular arch and inverse relationship between the maxillary and mandibular intermolar width resulted in posterior crossbite were confirmed by model analysis of the patient. These were not observed in the twins. Behaviorally, poor cooperation during dental treatment because of mental retardation was observed in the patient.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.166-173
• /
• 2024

This study explores lip-sync detection, focusing on the synchronization between lip movements and voices in videos. Typically, lip-sync detection techniques involve cropping the facial area of a given video, utilizing the lower half of the cropped box as input for the visual encoder to extract visual features. To enhance the emphasis on the articulatory region of lips for more accurate lip-sync detection, we propose utilizing a pre-trained visual attention-based encoder. The Visual Transformer Pooling (VTP) module is employed as the visual encoder, originally designed for the lip-reading task, predicting the script based solely on visual information without audio. Our experimental results demonstrate that, despite having fewer learning parameters, our proposed method outperforms the latest model, VocaList, on the LRS2 dataset, achieving a lip-sync detection accuracy of 94.5% based on five context frames. Moreover, our approach exhibits an approximately 8% superiority over VocaList in lip-sync detection accuracy, even on an untrained dataset, Acappella.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.153-163
• /
• 2003

In this paper, we propose a new technique of image based rendering(IBR) for the pose transformation of a face by using only a frontal face image and its mesh without a three-dimensional model. To substitute the 3D geometric model, first, we make up a standard mesh set of a certain person for several face sides ; front. left, right, half-left and half-right sides. For the given person, we compose only the frontal mesh of the frontal face image to be transformed. The other mesh is automatically generated based on the standard mesh set. And then, the frontal face image is geometrically transformed to give different view by using Invertible Meshwarp Algorithm, which is improved to tolerate the overlap or inversion of neighbor vertexes in the mesh. The same warping algorithm is used to generate the opening or closing effect of both eyes and a mouth. To evaluate the transformation performance, we capture dynamic images from 10 persons rotating their heads horizontally. And we measure the location error of 14 main features between the corresponding original and transformed facial images. That is, the average difference is calculated between the distances from the center of both eyes to each feature point for the corresponding original and transformed images. As a result, the average error in feature location is about 7.0% of the distance from the center of both eyes to the center of a mouth.