• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.767-777
• /
• 2023

In modern society, user privacy is emerging as an important issue as closed-circuit television (CCTV) systems increase rapidly in various public and private spaces. If CCTV cameras monitor sensitive areas or personal spaces, they can infringe on personal privacy. Someone's behavior patterns, sensitive information, residence, etc. can be exposed, and if the image data collected from CCTV is not properly protected, there can be a risk of data leakage by hackers or illegal accessors. This paper presents an innovative approach to "machine learning based reversible chaotic masking method for user privacy protection in CCTV environment." The proposed method was developed to protect an individual's identity within CCTV images while maintaining the usefulness of the data for surveillance and analysis purposes. This method utilizes a two-step process for user privacy. First, machine learning models are trained to accurately detect and locate human subjects within the CCTV frame. This model is designed to identify individuals accurately and robustly by leveraging state-of-the-art object detection techniques. When an individual is detected, reversible chaos masking technology is applied. This masking technique uses chaos maps to create complex patterns to hide individual facial features and identifiable characteristics. Above all, the generated mask can be reversibly applied and removed, allowing authorized users to access the original unmasking image.

• Archives of design research
• /
• v.17 no.3
• /
• pp.39-50
• /
• 2004

According to the survey done among the 20s of university students in Oct. 2002, the female animation characters from Korea and Japan have almost no distinction. Speaking of the features of the characters, they have big eyes, a long nose, an oval face. However, their eyes and mouths are expressed exaggeratedly, which makes them hard to get a good impression from the people. It seems that the identity of Korean female animation characters is disappearing in terms of the copycat from western animation characters. Through the research, the features of 20s of Korean and Japanese girls are compared and they were reviewed from the ideal and biological point of view. Then, the animation characters, which physiognomy has been applied, are created based on result, which I am trying to find the standard model of Korea female animation character. As an ideal point of view, it turns out that Korean has a positive reaction on the female animation characters with the cute & introspective characteristics. On the contrary, Korean has a negative reactions on the ones that were created in a biological viewpoint and has a highly sensitive and discontented characteristics. This shows that Korean do not prefer the female animation characters with highly sensitive and discontented characters. According to the survey, 73.5% of people could find the same 7 kinds of female characters which are shown frequently in the animation. This means that the oriental physiognomy is an effective way to approach to the features of the character's face depending on the characteristics of each female characters. The characters in this study are based on real face of female, but we can create the various animation characters if we apply the partial feature of distinctive each personal face.

• Korean Journal of Cognitive Science
• /
• v.33 no.2
• /
• pp.95-107
• /
• 2022

Facial processing of different racial origin has been investigated at various levels including perceptual, emotional, and socio-cultural processing. Particularly, a good deal of studies have been conducted to show "other race effect (ORE)" to indicate that subtle facial information such as identity or emotional expressions are often under-processed in racial out-group members. However, few studies have investigated whether attentional modulation toward racial out-group faces could explain ORE. We investigated whether novelty-driven attentional mechanism is involved in face perception using event-related potential (ERP). Twenty-two Korean (KR) and nine Caucasian-American (AM) participants were presented with emotional faces from the two racial origins while they performed a gender categorization task. KRs showed significantly greater P3 amplitudes to AM than to KR faces indicating that the early attentional processing underlies differential perception of racial out-group faces. Interestingly, P3 was not up-regulated in the AM subjects when they were presented with KR faces, perhaps due to massive habituation to KR faces during everyday social interaction. These results indicate that racial out-group faces are highly salient stimuli which automatically occupy attentional resources, but easily habituated with repeated exposure to the racial-out group.

• Journal of Acupuncture Research
• /
• v.33 no.1
• /
• pp.79-93
• /
• 2016

Objectives : The purpose of this study is to explore research trends in gold implantation therapy performed on the animal and human body, through a review of clinical studies focused on gold thread, gold needle and gold bead. Methods : Medical databases, including Pubmed, CENTRAL, MEDLINE, EMBASE, RISS4u, KISTI, OASIS and KTKP, were searched for relevant articles published from their launch to December 31, 2015 using the key word 'gold' with '$thread^*$', '$needle^*$', '$acupuncture^*$', '$wire^*$', '$bead^*$', '$embed^*$', '$implant^*$', or '$insert^*$'. The results were classified into in vivo studies, clinical trials and clinical reports. Analysis of the results was conducted in several research areas, from the identity of studies such as nationality and published year, to the gold preparations-features and implanted locations and to the outcomes that reflect the clinically favorable or adverse effect of gold implantation therapy. Results : A total of 30 studies including 11 in vivo studies, 4 clinical trials and 15 case reports, were found in the search. We observed certain research trends according to the research time, nationality and target indication of the studies. The studies primarily revealed a chronic local inflammatory response which could be a useful mechanism for pain-relief in musculoskeletal diseases and facial rejuvenation. Researches concerning long-term reactions or adverse effects were rare. Conclusion : The results show that the efforts to discover the level of clinical efficacy of gold implantation therapy were steady and worldwide. However, further researches on the longterm effect, and more importantly, the safety of gold implantation therapy are required.

• Journal of the Korean Society of Costume
• /
• v.54 no.7
• /
• pp.135-150
• /
• 2004

The purpose of this research was intended to investigate drag queens' and drag kings' gender identity not only as a comic and desexualized drag borrowing external characteristics of the opposite sex but also as the subject visualizing and performing' the third sex'. It also aimed to examine formative aesthetic characteristics and aesthetical value of drag queen's and drag king's fashion and to confirm the functions of drag queen's and drag kins's fashion to establish, visualize and Perform the discordant sex. For this process, research steps were as follows : 1. Understanding drag, drag queen and drag king in social, psychological context as well as in gender context. 2. Finding visualized forms which drag performance interchange with mass media 3. Analyzing similarities and differences between drag queen's fashion and drag king's fashion. 4. Examining the aesthetical characteristics and the value of drag queen's and drag king's fashion. The results of characteristics of drag queen's fashion could be categorized into stereotype, mimicry, kitch, inconsistency and commercialism. And the characteristics of drag king's fashion could be divided into reality, self-consciousness, mimicry, inconsistency, subversion and multiplicity. Drag queens create plausible impressions of feminity through the use of wigs, dresses, jewelry, makeup, hormones and through &role Playing&. Similarly drag kings produce a plausible masculinity taking gay male aesthetic using suits, crotch stuffers, facial hair, and greased hair. Male and female impersonation produce very different notions of gender performance for male and female embodiment. Drag kings' performance of masculinity demands authentic property of bodies so rather nonperformative, while drag queens' performance of femininity depends on more visible and theatrical fashion.

• Journal of Service Research and Studies
• /
• v.5 no.2
• /
• pp.93-101
• /
• 2015

Today, various access security technology appeared in this society as a result of the informatization and automation. Most building, floor, or door security certification system for the office units are installed, but there are many inconvenient matters. In order to minimises this, we used the face recognition function via the camera, and various sensors. In this paper, I designed the access security system through physical computing which Arduino offered, facial recognition program, and Twitter. Check that the personal information stored in the individual RFID tag is matched to the personal information stored on the existing server. Face recognition program input the face using a camera, and allow to confirm the identity. The system's abnormal or when the unauthenticated person is to penetrate, the system transmits the Twitter status message to the manager. It was designed continuously to monitor the status in real time in this way.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• Analytical Science and Technology
• /
• v.37 no.3
• /
• pp.189-199
• /
• 2024

In forensic genetics, when it is not possible to confirm an individual's identity through STR profile analysis, additional information about the individual can be obtained using DNA-based phenotypic traits estimation. Recently, various researches have been conducted on methods to determine externally visible characteristics (EVC) such as eyes, hair, and skin color. However, relying solely on such phenotypic traits information has limitations for application in East Asian regions, including Korea. In this study, in order to utilize EVC related to an individual's appearance as investigative information, SNPs related to eye shape, hair thickness, skin color, as well as baldness, body type, high myopia, facial shape, acne, and behavioral habits were explored. A total of 50 SNPs were selected, and a targeted amplicon NGS panel capable of amplifying them all at once was developed. Experimental results confirmed the allelic types and frequencies of the 50 SNPs in 14 samples. We plan to use this panel to investigate the correlation between genotype and phenotype using various samples, and to develop methods for interpreting the results.

• Archives of design research
• /
• v.19 no.1 s.63
• /
• pp.215-224
• /
• 2006

As the competition becomes more severe, the importance of brand confidence is coming to the front mainly because there has been a tendency of the customer for choosing a product or service in conjunction with the confidence. The concept of brand personality has formed as a result of various efforts for establishing a differentiated and confident brand image. The brand personality is regarded a useful mean for meeting objectives of a corporation for establishing a distinctive brand identity as well as customers for expressing their self-image. In line with the growing importance of the brand personality, researchers have attempted to measure it by various methods. However, most of researches were based on verbal and quantitative methods which take a long period of time and lots of efforts to analyze their results. Such methods also have limitations for visualizing the results. In this vein, this study aims to develop a new visible brand personality measurement system by utilizing the purpose-designed avatar. Major findings of the study are as follows: Firstly, the avatar can be an effective mean for visualizing the brand personality. As the avatar can visualize the personalities of human-beings through facial expressions, clothing, attitudes and movements, a specially designed avatar can express the brand personality. Secondly, types of the brand personality can be segregated into distinctive seven classes and such classes are used as guidelines for developing specially designed brand personality avatars. Thirdly, the purpose-designed brand personality avatar can be an effective mean for measuring the brand personality as a result of various tests for the validity. In condusion, avatar can be a more powerful tool than language for measuring the brand personality.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.183-191
• /
• 2010

Unique and invariant biometric characteristics have been used for secure user authentication. Storing original biometric data is not acceptable due to privacy and security concerns of biometric technology. In order to enhance the security of the biometric data, the cancelable biometrics was introduced. Using revocable and non-invertible transformation, the cancelable biometrics can provide a way of more secure biometric authentication. In this paper, we present a new cancelable bits extraction method for the facial data. For the feature extraction, the Subpattern-based Principle Component Analysis (PCA) is adopted. The Subpattern-based PCA divides a whole image into a set of partitioned subpatterns and extracts principle components from each subpattern area. The feature extracted by using Subpattern-based PCA is discretized with a helper data based method. The elements of the obtained bits are evaluated and ordered according to a measure based on the fisher criterion. Finally, the most discriminative bits are chosen as the biometric bits string and used for authentication of each identity. Even if the generated bits string is compromised, new bits string can be generated simply by changing the helper data. Because, the helper data utilizes partial information of the feature, the proposed method does not reveal privacy sensitive biometric information of the user. For a security evaluation of the proposed method, a scenario in which the helper is compromised by an adversary is also considered.