• Journal of information and communication convergence engineering
• /
• v.3 no.2
• /
• pp.110-113
• /
• 2005

An enhancement of tracking capacity for the centering position of eye and iris on the facial image is presented. A facial image is acquisitioned with a CCD camera to be converted into a binary image. The eye region to be a specified brightness and shapes is used the FRM method using the neighboring five mask areas, and the iris on the eye is tracked with FPDP method. The experimental result shows that the proposed methods lead the centering position tracking capability to be enhanced than the pixel average coordinate values method.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.4
• /
• pp.1657-1662
• /
• 2017

Facial expression recognition systems using video devices have emerged as an important component of natural human-machine interfaces which contribute to various practical applications such as security systems, behavioral science and clinical practices. In this work, we present a new method to analyze, represent and recognize human facial expressions using a sequence of facial images. Under our proposed facial expression recognition framework, the overall procedure includes: accurate face detection to remove background and noise effects from the raw image sequences and align each image using vertex mask generation. Furthermore, these features are reduced by principal component analysis. Finally, these augmented features are trained and tested using Hidden Markov Model (HMM). The experimental evaluation demonstrated the proposed approach over two public datasets such as Cohn-Kanade and AT&T datasets of facial expression videos that achieved expression recognition results as 96.75% and 96.92%. Besides, the recognition results show the superiority of the proposed approach over the state of the art methods.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.385-388
• /
• 2011

Patients' privacy protection is a heated issue in medical business, as medical information in digital format transmit everywhere through networks without any limitation. A current protection method for brain images is to deface from the brain image for patient's privacy. However, the defacing process often removes important brain voxels so that the defaced brain image is damaged for medical analysis. An ad-hoc method is proposed to conceal patient's identification by adding cylindrical mask, while the brain keep all important brain voxels. The proposed lossless deformation of brain image is verified not to loose any important voxels. Futhermore, the masked brain image is proved not to be recognized by others.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.944-947
• /
• 2022

Due to the coronavirus pandemic, the wearing of a mask has been increasing worldwide; thus, the importance of image analysis on masked face images has become essential. Although head pose estimation can be applied to various face-related applications including driver attention, face frontalization, and gaze detection, few studies have been conducted to address the performance degradation caused by masked faces. This study proposes a new data augmentation that synthesizes the masked face, depending on the face image size and poses, which shows robust performance on BIWI benchmark dataset regardless of mask-wearing. Since the proposed scheme is not limited to the specific model, it can be utilized in various head pose estimation models.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.748-757
• /
• 2017

In order to recognize the facial expressions, good features that can express the facial expressions are essential. It is also essential to find the characteristic areas where facial expressions appear discriminatively. In this study, we propose a directional LBP feature for facial expression recognition and a method of finding directional LBP operation and feature region for facial expression classification. The proposed directional LBP features to characterize facial fine micro-patterns are defined by LBP operation factors (direction and size of operation mask) and feature regions through AdaBoost learning. The facial expression classifier is implemented as a SVM classifier based on learned discriminant region and directional LBP operation factors. In order to verify the validity of the proposed method, facial expression recognition performance was measured in terms of accuracy, sensitivity, and specificity. Experimental results show that the proposed directional LBP and its learning method are useful for facial expression recognition.

• Korean Journal of Psychosomatic Medicine
• /
• v.32 no.1
• /
• pp.10-23
• /
• 2024

This study examines the changes in attractiveness and social perception of mask wearers during the COVID-19 pandemic. Before COVID-19, masks were seen as a sign of infection, decreasing the wearer's attractiveness. However, with the widespread normalization of mask-wearing during the pandemic, the perception mechanisms have become more complex. The attractiveness and social perception of mask wearers now vary based on factors such as the wearer's baseline attractiveness, race, and attitudes toward masks. Consequently, research findings on perception changes due to mask-wearing have been inconsistent. This inconsistency is due to the lack of standardized experimental methods and the failure to account for individual differences among participants, as well as insufficient theoretical background in the studies. From a psychiatric perspective, it is essential to formulate and test new hypotheses centered around the psychological mechanisms related to the human behavioral immune system when studying attractiveness perception during a pandemic. Notably, attention should be given to how differences in the activation of individuals' behavioral immune systems influence perceptions of mask wearers. Understanding these dynamics can provide crucial insights into how social perceptions and aversions impact mental health, thereby shedding light on various psychiatric issues that arise during infectious disease outbreaks.

• The korean journal of orthodontics
• /
• v.28 no.4 s.69
• /
• pp.533-546
• /
• 1998

A Skeletal Class III malocclusion may be the result of a large mandible, a small maxilla or combination of the two. Protraction devices for the maxilla are used to promote the growth of a deficient maxilla by applying extraoral force to actively growing patients. This study has been performed to determine whether there are significant differences in skeletal and dental changes between FH/Pal 1 and FH/Pal 2 group, SNA 1 and SNA 2 group, SNB 1 and SNB 2 group, and LFH 1 and LFH 2 group after RME and facial mask therapy. The results of this study can be summarized and concluded as follows ; 1. In all patients after maxillary protraction, the maxilla and maxillary dentitions moved forward, and the mandible rotated backward and downward. In most of them, palatal plane is tends to have an upward inclination. 2. The FH/Pal group 1, having an upward inclination of the palatal plane as a result of Facial mast showed statistically significant maxillary forward movement compared to the FH/Pal group 2. 3. The SNA group 1 showed significantly less mandibular backward movement and there was a tendency for the palatal plane to upward inclination compared to SNA group 2. 4. The SNB group 1 showed significantly less maxillary forward movement, but the vertical dimension, especially the lower facial height increased by mandibular downward rotation compared to SNB group 2. 5. LFH group 1, which had large saddle angle and posterior positioned mandible in the pre-treatment stage, showed maxillary protraction effect without significant increase in lower facial height compared to LFH group 2.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.26 no.3
• /
• pp.350-366
• /
• 2016

Objectives: No 3D anthropometric analyses have been conducted for Korean children's faces for the purpose of designing respiratory protective devices. The aim of this study was to develop masks against yellow dust and fine particulates, particularly for children in Korea. Methods: This study utilized a 3D scanning method to obtain 16 facial anthropometric data from children, ages of 5 to 13 years old. A total of 144 boys and girls were recruited from the kindergarten, elementary schools and middle schools in Seoul. With facial dimensions obtained, cluster analysis was performed to categorize them into similar facial groups. For each cluster, an optimal mask was designed and manufactured using a 3D printer. In addition, lung function data were obtained from 62 subjects and compared with those of normal adults. The pulmonary physiological results were subsequently used to suggest a test method for mask certification. Results: Facial shapes were classified into tree clusters: small, medium, and large. The face width and length for the first group were small with high nosal protrusion. The face width and length for the second group were the largest among the three clusters. The third group had the largest angle of nose root - gnathion(n-prn-gn). Age was the most significant variable in the facial dimensions. Children's pulmonary physiological capacity was about 60% of adults' capacity. The results of fit test using the prototype masks developed showed very good fits for children. Conclusions: For Korean children, three mask sizes will be sufficient and practical for providing protection against yellow dust and fine particulates. Anthropometric data obtained using digitalized 3D face analysis can be very effective for designing respiratory devices. 3D images can be accurate and easily measured for multiple dimensions, particularly for curved areas of the face. It is imperative to adopt different test methods for certifying respiratory protective devices for children, since their pulmonary physiological capacity is inferior compared with that of adults.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.1
• /
• pp.62-69
• /
• 2018

In order to utilize health food chick bean as a raw material for cosmetics, the skin improvement effect of a mask pack made of chickpea Natto fermented with Bacillus subtilis Natto strain was studied. Powder obtained by lyophilization of chickpea Natto was applied to a facial mask pack as a paste formulation. This Natto pack was applied to subjects in their 50s and 60s to investigate their effect on skin improvement. As the number of treatments of Natto pack increased, the skin was improved and the improvement effect was remarkable after 4 treatments. After four times treatments, moisture content and sebaceous secretion increased by $8.4{\pm}3.6%p$ and $4.0{\pm}2.3%p$, respectively. Skin pores and wrinkles were also decreased by $1.8{\pm}0.3%p$ and $1.8{\pm}0.9%p$, respectively. Skin pigmentation decreased by $1.3{\pm}0.2%p$ and skin tone also increased from 55.2% to 55.9%. These results indicate that Natto product obtained by fermenting chickpea has the effect of improving skin such as moisturizing, pore, wrinkle, pigmentation, sebum secretion and skin tone, and can be used as a raw material for various functional cosmetics.