안면 색상 데이터 분석 기반의 퍼스널 컬러 진단 및 가상 메이크업 애플리케이션 개발

안예은,이규빈,정수현,김희수,유제혁 한국영상학회 2024 한국영상학회 논문집 Vol.22 No.2

최근, 뷰티 산업시장의 성장과 함께 개인의 아름다움을 더욱 부각할 수 있는 퍼스널 컬러의 관심도가 증가하고 있다. 오프라인 기반의 퍼스널 컬러 진단의 경우, 전문가의 관능 평가에 의해 퍼스널 컬러 진단이 이루어지며, 온라인 기반 퍼스널 컬러 진단의 경우, 사용자의 안면 촬영 이미지를 활용하여 애플리케이션 기반의 퍼스널 컬러 진단이 이루어진다. 간편성 및 저비용의 이유로 활용되는 온라인 퍼스널 컬러 진단의 경우, 사용자 안면 촬영 시, 광원 영향, 노이즈 등 환경 조건에 영향을 받기 때문에 진단 정확도가 떨어지는 문제가 발생한다. 또한, 기존 퍼스널 컬러 진단 서비스들의 경우, 실제와 같은 가상 메이크업이 이루어지고 있지 않기 때문에, 심미적인 체험을 진행할 수 없다는 단점이 존재한다. 본 연구는 일관성 있는 온라인 퍼스널 컬러 진단을 목표로 하여, 촬영된 사용자 안면 이미지를 다양한 색상 공간상에서 분석하고 대표 피부 색상을 추출하는 알고리즘에 대해 제안한다. 정확한 퍼스널 컬러 분석을 위해, YOLOv5 기반 객체 인식 딥러닝 모델을 활용하여 퍼스널 컬러 진단 저해 요소들을 제거하였으며, 군집화 기반의 데이터 분석 알고리즘 통해 대표 안면 색상을 도출하였다. 대표 안면 색상을 기반으로 퍼스널 컬러 유형을 진단하였으며, 최종적으로 진단된 퍼스널 컬러 기반으로, 사용자에게 심미적인 체험을 제공할 수 있는 가상 메이크업 기능을 추가하여 제공하였다. 가상 메이크업은 생성형 딥러닝 모델인 BeautyGAN을 이용하여 사용자별 가장 조화로운 메이크업 모습을 보여주게 되며, 이를 통해 자신에게 가장 어울리는 메이크업 아이템들을 능동적으로 선별할 수 있다. Recently, with the growth of the beauty industry, there has been increasing interest in personal colors that stand out in relation to individual beauty. With regard to an offline-based personal color diagnosis, experts conduct the diagnosis based on a sensory evaluation, while an online-based personal color diagnosis utilizes application-based methods that involve analyzing user-captured facial images. However, the online-based personal color diagnosis, widely used for its convenience and low cost, faces challenges related to accuracy due to factors such as lighting conditions and noise that arise when the user captures their facial image. Moreover, existing personal color diagnosis services lack the ability to provide a virtual makeup experience that closely resembles reality. This study aims to achieve consistent online personal color diagnosis results by proposing an algorithm that analyzes user-captured facial images in various color spaces and extracts representative skin colors. To ensure an accurate personal color analysis, potential hindrances to personal color diagnoses were eliminated using a YOLOv5-based object-recognition deep-learning model. Additionally, a clustering-based data analysis algorithm was employed to derive representative facial colors. Based on these representative facial colors, the study diagnosed personal color types and ultimately provided users with a virtual makeup function that enhances their aesthetic experience. The virtual makeup feature uses the BeautyGAN generative deep-learning model to show the most harmonious makeup styles for each user, enabling them to actively select makeup items that best suit their preferences.

An Exploratory Study of Generative AI Service Quality using LDA Topic Modeling and Comparison with Existing Dimensions

안예은,오정석 서비스사이언스학회 2023 서비스연구 Vol.13 No.4

Artificial Intelligence (AI), especially in the domain of text-generative services, has witnessed a significant surge, with forecasts indicating the AI-as-a-Service (AIaaS) market reaching a valuation of $55.0 Billion by 2028. This research set out to explore the quality dimensions characterizing synthetic text media software, with a focus on four key players in the industry: ChatGPT, Writesonic, Jasper, and Anyword. Drawing from a comprehensive dataset of over 4,000 reviews sourced from a software evaluation platform, the study employed the Latent Dirichlet Allocation (LDA) topic modeling technique using the Gensim library. This process resulted the data into 11 distinct topics. Subsequent analysis involved comparing these topics against established AI service quality dimensions, specifically AICSQ and AISAQUAL. Notably, the reviews predominantly emphasized dimensions like availability and efficiency, while others, such as anthropomorphism, which have been underscored in prior literature, were absent. This observation is attributed to the inherent nature of the reviews of AI services examined, which lean more towards semantic understanding rather than direct user interaction. The study acknowledges inherent limitations, mainly potential biases stemming from the singular review source and the specific nature of the reviewer demographic. Possible future research includes gauging the real-world implications of these quality dimensions on user satisfaction and to discuss deeper into how individual dimensions might impact overall ratings.

1인 가구를 위한 공동구매 및 정보 공유 커뮤니티 서비스

이예은(Yeeun Lee),김규리(Gyuree Kim),이해서(Haeseo Lee),정은혜(Eun-Hye Jeong),안형태(Hyeongtae Ahn),오병우(Byoung-Woo Oh) 한국정보기술학회 2022 Proceedings of KIIT Conference Vol.2022 No.6

국내 1인 가구의 비중이 커지면서 이와 관련된 맞춤 서비스의 수요 또한 증가하고 있다. 이러한 사회적 흐름에 주목하여 1인 가구 관련 서비스가 개발되고 있다. 그러나 사용자의 요구를 종합하여 다양한 기능을 제공하는 시스템을 찾기는 어렵다. 현 상황을 고려하여 본 논문에서는 1인 가구를 위한 맞춤형 커뮤니티 서비스를 제안한다. 본 논문에서 제안하는 서비스는 사용자의 경제적 부담을 줄이기 위해 배달 및 배송 공동구매와 OTT 플랫폼 공유 구독자 모집을 지원한다. 그리고 1인 가구 정책 및 유용한 생활 정보를 공유할 수 있다. As the proportion of single-person households in Korea increases, the demand for customized services related to this is also increasing. Paying attention to these social trends, services related to single-person households are being developed. However, it is difficult to find a system that provides various functions by synthesizing user needs. Considering the current situation, this paper proposes a customized community service for single-person households. The service proposed in this paper supports the group purchase of delivery and delivery and the recruitment of OTT platform sharing subscribers to reduce the economic burden of users. You can also share single-person household policies and useful life information.

CISG 제42조하에서 매도인의 책임에 관한 연구 : CISG 자문위원회 공식의견서 제22호를 중심으로

이병문,안예은 한국무역학회 2023 한국무역학회 학술대회 Vol.2023 No.12

겨울철 천식 환자 가정의 실내공기 중 부유진균의 농도 및 다양성

정인희,김예은,알라무디 알라 아이에드,안금란,김성환 한국냄새환경학회 2022 실내환경 및 냄새 학회지 Vol.21 No.1

. Fungi have been known as an irritant or causal agent of asthma. Thus, information on their concentration and diversity in indoor air of asthmatic patient’s houses is valuable for the management of these micro-organisms. The present study was performed to investigate fungal concentration and diversity in indoor air of resident spaces in two adult patient’s houses in winter. Air samples were collected in February of 2018 from living rooms and bedrooms of two asthma patients’ houses located in two different places in Incheon city using an impaction method. The average concentrations of airborne fungi did not exceed the 500 CFU/m3 level which is recommended by the Enforcement Managements of the Indoor Air Quality, Ministry of Environment, Korea. A total of four genera and 23 species were identified based on morphological and molecular methods. Aspergillus and Penicillium were two major genera. Aspergillus pseudoglaucus and Penicillium citrinum were commonly found between the two patient’s houses. Among the identified fungi, three species, Aspergillus venenatus, Penicillium jamesonlandense, and Penicillium salami were found to be unrecorded species in Korea. The morphological and molecular characteristics of these three unrecorded species were described. Since these species produce spores well and a lot, they are considered to be a species that needs management. This study provides basic information on the fungi for indoor air quality management in the living spaces of asthma patients in winter in Korea.

나라기록관 미소독 서고의 실내공기중 부유세균 조사

김수산,김예은,노형진,이동형,김준영,안금란,김성환 한국냄새환경학회 2021 실내환경 및 냄새 학회지 Vol.20 No.1

To obtain information on the indoor air quality of un-disinfected libraries used for paper records preservation, temperature, humidity, and bacterial concentration and species were investigated at five un-disinfected libraries from May to September in 2019 in the National Archives, Seoul (Nara Repository), Korea. Temperature and humidity of all the five un-disinfected libraries were well maintained at 18-22oC and 40-55% in compliance with the National Archives Paper Records Preservation Environment Standard. Bacterial concentration ranged from 2 CFU/m3 up to 280 CFU/m3 which were lower than the Korean indoor air quality standard value. A total of 68 bacterial species belonging to 33 genera were identified from indoor air of the five un-disinfected libraries. Among the 33 genera, Bacillus, Micrococcus, and Staphylococcus were the major genera. Only Micrococcus yunnanensis, Roseomonas mucosa, and Moraxella osloensis were commonly found among the five un-disinfected libraries. Bacterial species producing colonies with color on TSA media were present. Among the 68 species, Bacillus circulans and B. megaterium known to produce cellulases were found. There were also 17 species which have harmful effect on human health. The results of this study indicate that continuous monitoring of air borne bacteria is necessary in the un-disinfected libraries used for paper records preservation.

블록체인 기술을 활용한 전자선하증권의 법적기반에 관한 연구 : 로테르담 규칙과 한국 상법의 실무적 적용을 중심으로

이병문,안예은 한국무역학회 2023 한국무역학회 세미나 및 토론회 Vol.2023 No.2

COVID-19 감염 후 발생한 시신경척수염범주질환

최종희,서범석,안예은,김재명,박만석,이승한 대한신경과학회 2024 대한신경과학회지 Vol.42 No.1

Coronavirus disease-19 (COVID-19) infection may be accompanied by various neurological complications. Among them, demyelinating disease involving the central nervous system has rarely been reported in association with COVID-19 infection. Herein, we report a case of newly diagnosed neuromyelitis optica spectrum disorder (NMOSD) right after COVID-19 infection. From our case, autoimmunity induced by para- and post-infectious immunologic responses or direct viral invasion might contribute to the development of NMOSD.

핵심기본간호술 실습교육이 간호학 전공 학생들의 핵심기본간호술 수행 자신감에 미치는 영향

소애영,서길희,박선아,이민지,안예은,이미송,박세진,박희주,김민관 한국간호교육학회 2016 한국간호교육학회 학술대회 Vol.2016 No.5

산채류로 제조된 장아찌의 항산화 활성

이예슬,임상희,최성령,최보배,안예은,김덕진,손호영 동아시아식생활학회 2013 동아시아식생활학회 학술발표대회논문집 Vol.2013 No.11