• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.1-7
• /
• 2023

The advent of deep learning technologies has led to the development of various medical applications, making healthcare services more convenient and effective. Among these applications, heart rate estimation is considered a vital method for assessing an individual's health. Traditional methods, such as photoplethysmography through smart watches, have been widely used but are invasive and require additional hardware. Recent advancements allow for contactless heart rate estimation through facial image analysis, providing a more hygienic and convenient approach. In this paper, we propose a lightweight methodology capable of accurately estimating heart rate in mobile environments, using a specialized 2-channel network structure based on 2D convolution. Our method considers both subtle facial movements and color changes resulting from blood flow and muscle contractions. The approach comprises two major components: an Encoder for analyzing image features and a regression layer for evaluating Blood Volume Pulse. By incorporating both features simultaneously our methodology delivers more accurate results even in computing environments with limited resources. The proposed approach is expected to offer a more efficient way to monitor heart rate without invasive technology, particularly well-suited for mobile devices.

• The Journal of Korean Academy of Prosthodontics
• /
• v.50 no.1
• /
• pp.1-9
• /
• 2012

Purpose: The purpose of this study was to investigate the effects of a mouthguard on stress distribution under mandibular impact. Materials and methods: The FEM model of head consisted of skull, maxilla, mandible, articular disc, teeth, and mouthguard. The impact locations on mandible were gnathion, the center of inferior border, and the anterior edge of gonial angle. And the impact directions were vertical, oblique ($45^{\circ}$), and horizontal. The impact load was 800 N for 0.1 sec. Results: When vertical impact was applied, the similar stress and the distribution pattern was occurred without the relation of the mouthguard use (P>.05). The model with mouthguard was dispersed the stress to the teeth, the facial bone and the skull when the oblique ($45^{\circ}$) impacts were happened. However, the stress was centralized on the teeth in the model without mouthguard(P<.05). The model with mouthguard was dispersed the stress to the teeth, the facial bone and the skull when the horizontal impacts was occurred. However, the stress was centralized on the teeth without mouthguard (P<.05). For all impact loads, stress concentrated on maxillary anterior teeth in model without mouthguard, on the contrary, the stress was low in the model with mouthguard and distributed broadly on maxillary anterior teeth, facial bone, and skull. Conclusion: The mouthguard was less effective at shock absorbing when vertical impact was added. However, it was approved that mouthguard absorbed the shock regarded to the oblique ($45^{\circ}$) and horizontal impact by dispersing the shock to the broader areas and decreasing the stress.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.299-302
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of$.$10 persons show that the proposed method yields high recognition rates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2496-2511
• /
• 2014

Face recognition is considered a complex biometrics in the field of image processing mainly due to the constraints imposed by variation in the appearance of facial images. These variations in appearance are affected by differences in expressions and/or occlusions (sunglasses, scarf etc.). This paper discusses incremental Kernel Fisher Discriminate Analysis on sub-classes for dealing with partial occlusions and variant expressions. This framework focuses on the division of classes into fixed size sub-classes for effective feature extraction. For this purpose, it modifies the traditional Linear Discriminant Analysis into incremental approach in the kernel space. Experiments are performed on AR, ORL, Yale B and MIT-CBCL face databases. The results show a significant improvement in face recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.822-826
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of 10 persons show that the proposed method yields high recognition rates.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.2
• /
• pp.95-98
• /
• 2014

Two-dimensional cephalometric analysis has been used for diagnosis and treatment of correction of mandibular asymmetry by many maxillofacial surgeons. And 2D analysis showed excellent results in many cases, however 2D has some drawbacks in diagnosis and treatment planning because of its fundamental limitation like overlapping. Today many physicians use 3D diagnosis & treatment tools to expect better results and reduce possible errors. The aim of this report is to present treatment procedures using 3D analysis and treatment modalities for mandibular asymmetry patients.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1586-1593
• /
• 2020

This study was conducted on the face ratio of mammals. It can also be applied to character automation by checking factors about the difference between animal and human face shapes. This paper used the face and face area data generated for Deep Learning learning. In detail, the proportion factors of the area comprising the faces of 20 species of animals and humans were defined and the average ratio was calculated. Next, the proportion of each animal was analyzed using the Principal Component Analysis (PCA). Through this, we would like to propose the golden ratio of mammals.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.17 no.3
• /
• pp.103-108
• /
• 2017

Kabuki syndrome is a rare congenital disorder that causes multiple birth defects and mental retardation. Mutation of the lysine methyltransferase 2D (KMT2D) gene is the primary cause of Kabuki syndrome. We report a 4-year-old Korean girl diagnosed with Kabuki syndrome based on distinctive facial features (eversion of the lower lateral eyelid, arched eyebrows, depressed nasal tip, prominent ears), skeletal anomalies, short stature, and molecular analysis, which revealed a novel frameshift mutation in the KMT2D gene. A 4-year-old patient had a past history of congenital cardiac malformations (coarctation of the aorta, ventricular septal defect, atrial septal defect, patent ductus arteriosus), subclinical hypothyroidism and dysmorphic features at birth including webbed neck, short fingers, high arched palate, micrognathia and horseshoe kidney. She showed unique facial features such as a long palpebral fissure, long eyelashes, arched eyebrows with sparseness of the lateral third, broad nasal root, anteverted ears, and small mouth. Her facial features suggested Kabuki syndrome, and genetic analysis discovered a novel heterozygous frameshift mutation (c.4379dup, p.Leu1461Thrfs*30) in exon 15 of the KMT2D gene. The diagnosis of our 4-year-old patient was made through thorough physical examination and history taking, and genetic testing. It is challenging to diagnose patients with Kabuki syndrome at birth, since the characteristic facial features are expressed gradually during growth. Clinical suspicion aroused by regular follow-ups may lead to earlier diagnosis and interventions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.295-298
• /
• 2007

본 논문에서는 사람의 얼굴표정을 통해 4개의 기본감정(기쁨, 슬픔, 화남, 놀람)에 대한 특징을 추출하고 인식하여 그 결과를 이용하여 감정표현 시스템을 구현한다. 먼저 주성분 분석(Principal Component Analysis)법을 이용하여 고차원의 영상 특징 데이터를 저차원 특징 데이터로 변환한 후 이를 선형 판별 분석(Linear Discriminant Analysis)법에 적용시켜 좀 더 효율적인 특징벡터를 추출한 다음 감정을 인식하고, 인식된 결과를 얼굴 표현 시스템에 적용시켜 감정을 표현한다.

• Journal of Multimedia Information System
• /
• v.2 no.1
• /
• pp.171-178
• /
• 2015

This article describes 3 dimensional (3D) face recognition system using histogram of oriented gradients (HOG) based on face curvature. The surface curvatures in the face contain the most important personal feature information. In this paper, 3D face images are recognized by the face components: cheek, eyes, mouth, and nose. For the proposed approach, the first step uses the face curvatures which present the facial features for 3D face images, after normalization using the singular value decomposition (SVD). Fisherface method is then applied to each component curvature face. The reason for adapting the Fisherface method maintains the surface attribute for the face curvature, even though it can generate reduced image dimension. And histogram of oriented gradients (HOG) descriptor is one of the state-of-art methods which have been shown to significantly outperform the existing feature set for several objects detection and recognition. In the last step, the linear discriminant analysis is explained for each component. The experimental results showed that the proposed approach leads to higher detection accuracy rate than other methods.