• 제목/요약/키워드: age of face

검색결과 758건 처리시간 0.024초

가림이 있는 얼굴 영상의 나이 인식 연구 (A study of age estimation from occluded images)

  • 최성은
    • Journal of Platform Technology
    • /
    • 제10권3호
    • /
    • pp.44-50
    • /
    • 2022
  • 얼굴 영상에서 나이를 인식하는 기술은 여러 응용분야에서 활용되면서 그에 대한 연구가 활발히 진행되고 있다. 다양한 환경에서 촬영된 얼굴 영상은 얼굴의 일부가 가려지는 경우가 많으며 이는 나이 인식 성능에 영향을 미치게 된다. 따라서 본 논문에서는 가림이 있는 얼굴 영상의 나이 인식 성능을 개선하기 위해, Image Extrapolation 기술을 이용하여 가려진 부분을 생성하여 나이를 인식하는 방법을 제안한다. 영상에서의 가림이 나이 인식 성능에 미치는 영향을 확인하기 위해서 마스크 이미지를 적용하여 가림이 있는 얼굴 영상을 생성하였다. 가림에 의해 나이 인식 성능이 저하되는 문제를 해결하기 위해, Image Extrapolation 기술 중 영상의 가장자리를 순회하면서 가려진 부분을 생성하는 SpiralNet 을 사용하여 가려진 부분을 예측하여 생성하고 얼굴 나이 인식에 사용하였다. 실험을 통해 가림이 있는 영상에서 나이 인식 성능이 저하되는 문제가 있고, SpiralNet으로 가림 부분을 생성한 영상으로 나이를 인식하면 나이 인식 성능이 개선되는 것을 확인하였다.

한국인 입에 대한 생체계측학적 연구 (Anthropometric Analysis of the Mouth in Koreans)

  • 김순흠;김나연;이수향;최현곤;신동혁;엄기일;이정용;송우철;고기석
    • Archives of Plastic Surgery
    • /
    • 제35권2호
    • /
    • pp.139-146
    • /
    • 2008
  • Purpose: The objective of this study is anthropometric analysis of mouth and lower face of Korean. The relationship of soft-tissue to underlying bony structures determine the overall aesthetics of the face. The goal of aesthetic surgery of the face is to achieve the ideal normal and enhance the aging face. The purpose of present study was to determine the change of the morphology of the mouth and lower face based on soft-tissue landmarks according to age group to facilitate prediction during aesthetic surgery. Methods: The standardized photographs of 2,018 healthy volunteers(18 to 79 years of age; 1,070 males, 948 females) were investigated. Age groups were classified into young, middle-aged, and elderly groups. Five and seven items were measured on frontal and lateral view photographs, respectively. Individual dimensions were compared in the three age groups and between males and females. Results: The width of mouth is 4.5 times larger than that of philtrum. Most of measured data decreased with age. However, woman's lip width of the mouth somewhat increased from the young to elderly. The width of lower face is 2.5 times larger than mouth in young age group and increased slightly from the young to middle-aged and thereafter slightly decreased to elderly group. Upper lip was more higher than lower lip and male lip was more higher than female. But male and female lip height is similar at old age. Conclusion: Most of Koreans showed prominent lower face because of the development or protrusion of the mandible. And the descent of soft-tissue around the mouth was one of the significant characteristics of senile change. The posterior retrusion of the subnasal was an another characteristic. This study will help to elucidate the age-related dimensional differences of the human being and to provide useful information for clinical applications in oral and aesthetic surgery.

한국 성인여성의 얼굴형태에 관한 연구 (A Study on the Facial Shape of Korean Women)

  • 이경화;김정희
    • 한국의류학회지
    • /
    • 제33권6호
    • /
    • pp.938-948
    • /
    • 2009
  • 본 연구는 2003년에서 2004년에 실시된 제 5차 한국인 인체치수 조사사업을 통해 확보된 측정사진 중 성인여성 20, 30, 40, 50대 각 150명, 총 600명의 정면과 측면 얼굴사진을 대상으로 얼굴의 연령별 특성을 파악하는데 필요하다고 판단되는 62개의 측정항목과 보다 세부적인 얼굴형태의 분석에 활용될 수 있는 21개의 지수 및 계산항목 총 83개 항목을 본 연구자가 선정한 후 Size Kroea 사업 중 얼굴의 측정 프로그램으로 사용되었던 "Venus face2D"를 이용하여 2차원 간접 측정하였다. 간접 측정기간은 2006년 3월 1일부터 6월 30일까지였다. 연구의 결과는 다음과 같다. 성인여성의 주요 측정항목에 대한 평균 측정치는 얼굴길이 196mm, 상안 62.3mm, 중안 68.9mm, 하안 66.5mm이었고, 이마너비는 125.1mm, 눈살수평너비는 141.2mm, 옆광대점너비 150.8mm 턱아래점너비 124.4mm였다. 이를 바탕으로 우리나라 성인여성 얼굴의 세부항목에 대한 연령집단별 차이를 분석하였으며, 전체 성인여성의 평균 얼굴형과 더불어 각 연령집단별 평균 얼굴형을 제시하였다. 본 연구는 정량화된 수치와 비율을 이용하여 우리나라 성인여성 및 각 연령별 평균 얼굴형을 제시하고, 연령별 얼굴특성을 분석하였다는데 연구의 의의가 있다.

화장행동과 영향 변인 연구 -의복관여도, 연령, 얼굴만족도를 중심으로- (Make-Up Behavior and Influential Factors - Focusing on Clothing Involvement, Age and Face Satisfaction -)

  • 백경진;김미영
    • 한국의류학회지
    • /
    • 제28권7호
    • /
    • pp.892-903
    • /
    • 2004
  • The purpose of this study was to analyze the differences in make-up behavior according to clothing involvement, age, and face satisfaction. Subjects of is study were the females in Seoul and Kyonggi, who were 20s and 40 $.$ 50s. Questionnaire was used as major method of gathering data. The data were collected from Sep. to Oct. in 2003 and analyzed by using SPSS 10.0 with various techniques such as the factor analysis, mean, percentage, cluster analysis, ANOVA, Duncan test, 1-test, Cronbach's $\alpha$, and $\chi$$^2$-test. The results of this study were as follows: 1. The consumers were classified into four categories by clothing involvement; high clothing involvement group, low fashion involvement group, middle clothing involvement group, low clothing involvement group. 2. The differences in make-up behavior according to the clothing involvement showed that make-up behavior was getting more aggressive as clothing involvement was getting higher. And generally Korean females thought the make-up was important. 3. The differences in make-up behavior according to the age revealed that 20s' make-up behavior was fashion oriented more than 40ㆍ50s, and 40ㆍ50s' make-up behavior was that they were taking a serious viewer than 20s' in interpersonal relationship oriented make-up behavior. 4. The result of differences in make-up behavior according to the face satisfaction was that no noticeable difference was found depending on the face satisfaction. This study revealed that the differences in make-up behavior according to clothing involvement and age were found and suggested that the cosmetic market segmentation could depend on clothing involvement market and two age group market such as younger and elder than 40ㆍ50s.

일반인이 선호하는 얼굴의 미적 단위별 형태와 비율 연구 (A Study on Preferred Morphologic Feature and Proportion of Facial Aesthetic Subunit by Korean General Public)

  • 윤용일;이동락;유중석;이승철;허지연;김주연
    • Archives of Plastic Surgery
    • /
    • 제37권4호
    • /
    • pp.351-360
    • /
    • 2010
  • Purpose: As the influence of mass media increases, the general standard of attractiveness or beauty of a face also changes. The primary purpose of the study is to find out the factors of the attractive and beautiful face recognized by public. Methods: We picked out standard model photography and operated with Adobe$^{(R)}$ Photoshop$^{(R)}$ and Monariza$^{(R)}$ virtual plastic surgery program. The contour of face, eye, nose, forehead, zygoma, chin and proportion of upper, middle, lower face were changed. The interview survey was conducted through structured standard photo for 310 respondents. That was utilized in the final analysis. Multiple regression analysis was executed by SPSS 12.0. It was used to deal with statistical data and all the other necessary analysis. Results: According to general characteristics of the respondents, many differences were found in preferred face and facial aesthetic subunits. The younger generation preferred the lozenge and inverted triangle shape contour. The respondents over 40 of age preferred the egg shape contour. In chin and zygoma contour, the respondents at the age of 20 preferred distinctly small chin and relatively small lower face. On the other hand, the respondents over 40 of age preferred the wide zygoma relatively. In the proportion of upper, middle, lower face, 51.0% of respondents answered 1 : 1 : 1. If they want to have an aesthetic operation, they preferred protruding forehead. Also they preferred the small chin and V-shaped chin in frontal view. Conclusion: Many respondents preferred to have a plastic surgery for the better facial subunit. The statistical evidence from this study suggests that the harmony and balance of facial aesthetic subunits make attractive and beautiful face.

나이변화를 위한 얼굴영상의 분석과 합성 (Analysis and Syntheris of Facial Images for Age Change)

  • 박철하;최창석;최갑석
    • 전자공학회논문지B
    • /
    • 제31B권9호
    • /
    • pp.101-111
    • /
    • 1994
  • The human face can provide a great deal of information in regard to his/her race, age, sex, personality, feeling, psychology, mental state, health condition and ect. If we pay a close attention to the aging process, we are able to find out that there are recognizable phenomena such as eyelid drooping, cheek drooping, forehead furrowing, hair falling-out, the hair becomes gray and etc. This paper proposes that the method to estimate the age by analyzing these feature components for the facial image. Ang we also introduce the method of facial image synthesis in accordance with the cange of age. The feature components according to the change of age can be obtainec by dividing the facial image into the 3-dimensional shape of a face and the texture of a face and then analyzing the principle component respectively using 3-dimensional model. We assume the age of the facial image by comparing the extracted feature component to the facial image and synthesize the resulted image by adding or subtracting the feature component to/from the facial image. As a resurt of this simulation, we have obtained the age changed ficial image of high quality.

  • PDF

MixFace: Improving face verification with a focus on fine-grained conditions

  • Junuk Jung;Sungbin Son;Joochan Park;Yongjun Park;Seonhoon Lee;Heung-Seon Oh
    • ETRI Journal
    • /
    • 제46권4호
    • /
    • pp.660-670
    • /
    • 2024
  • The performance of face recognition (FR) has reached a plateau for public benchmark datasets, such as labeled faces in the wild (LFW), celebrities in frontal-profile in the wild (CFP-FP), and the first manually collected, in-the-wild age database (AgeDB), owing to the rapid advances in convolutional neural networks (CNNs). However, the effects of faces under various fine-grained conditions on FR models have not been investigated, owing to the absence of relevant datasets. This paper analyzes their effects under different conditions and loss functions using K-FACE, a recently introduced FR dataset with fine-grained conditions. We propose a novel loss function called MixFace, which combines classification and metric losses. The superiority of MixFace in terms of effectiveness and robustness was experimentally demonstrated using various benchmark datasets.

차세대 공항 서비스를 위한 베이지안 연령추정기법을 이용하는 스마트 디지털 사이니지에 대한 연구 (A Study on a Smart Digital Signage Using Bayesian Age Estimation Technique for the Next Generation Airport Service)

  • 김춘호;이동우;백경민;문성엽;허찬;나종화;온승엽;최우영
    • 한국항행학회논문지
    • /
    • 제18권6호
    • /
    • pp.533-540
    • /
    • 2014
  • 차세대 공항 서비스를 위하여 고객의 연령 정보를 인식하는 스마트 디지털 사이니지를 제안한다. 제안된 시스템은 고객의 얼굴을 검출하고 연령대를 베이지안 분류기법을 이용하여 추정하여 맞춤형 정보를 디스플레이 함으로서 고객의 만족도를 향상시키도록 설계되었다. 연령대 인식은 카메라를 이용하여 고객의 얼굴 영상을 획득한 뒤, 얼굴의 주름을 계산하고 베이지안 분류기를 이용하여 연령대를 추정한다. 개발된 연령대 인식기반 스마트 디지털 사이니지는 영상시스템 평가용 FERET 얼굴 데이터베이스를 이용하여 성능을 검증하였다. 연령추정 스마트 디지털 사이니지는 다양한 연령대의 공항고객에게 맞춤형 광고를 제시함으로서 광고 효율을 개선하여 공항 고객의 만족도 향상에 기여할 수 있을 것으로 기대된다.

얼굴형 인공지능 스피커에 대한 선호의 나이 효과 (Age differences of preference for humanoid AI speakers)

  • 오성주;황지현;유지호;한소원
    • 인지과학
    • /
    • 제29권1호
    • /
    • pp.1-16
    • /
    • 2018
  • 본 연구에서 얼굴형 인공지능 스피커에 대한 선호도와 신뢰도가 나이에 따라 어떻게 달라지는지 살펴보았다. 인공지능 스피커의 외형은 성별(남녀)과 나이(20/60대) 네 가지 범주에서 로봇 얼굴과 사람 얼굴이 7단계로 혼합되어 제시되었다. 참여자들 역시 이 네 가지 범주에 맞춰 모집되었고, 각 범주의 얼굴 자극에 대한 호감도와 신뢰도를 7점 척도로 평가하였다. 연구 결과, 인공지능 스피커의 외형이 사람 얼굴을 닮을수록 노인들은 호감도와 신뢰도를 높게 평가했지만, 청년들은 로봇 얼굴과 사람 얼굴이 중간 정도 섞인 형태를 가장 선호하고 신뢰하여 전체적으로 뒤집힌 U자 형태의 평가를 보였다. 네 가지 얼굴 범주에서 선호도를 평가했을 때, 참여자들은 나이와 성별과 관계없이 젊은 얼굴이 가장 높은 점수를 받았다. 그런데, 이모티콘 얼굴과 얼굴이 없이 비어있는 조건을 추가하여 물었을 때, 여전히 노인들은 사람 얼굴을 가장 선호했지만, 청년들은 상대적으로 이모티콘 얼굴과 비어있는 조건을 더 선호하였다. 종합하면, 인공지능 스피커 맥락에서, 노인들은 청년들보다 로봇 얼굴이 아닌 사람 얼굴에 높은 수용적 태도를 보였다. 홀로 사는 노인 인구가 증가하는 미래에 인공지능 스피커의 역할이 중요해짐에 따라, 노인들을 위한 인공지능 스피커의 디자인과 개발에서 본 연구 결과가 좋은 참고가 될 것으로 기대된다.

30${\sim}$40대 한국 여성의 안색과 혈행의 상관성 연구 (The correlation of the skin color to the blood circulation on the face of Korean female between the ages of 30 and 45)

  • 김은주;노호식;김수정;문은정;김덕희;김한곤;조가영
    • 대한한의정보학회지
    • /
    • 제14권2호
    • /
    • pp.73-79
    • /
    • 2008
  • Objectives : We investigated the correlation of the skin color to blood circulation on the face of Korean female by noninvasive-skin measuring devices. Methods : Korean female(37.47${\pm}$3.66 years, n=36) aged 30-45 years were participated in this study. We measured the skin color of the face with Spectrophotometer CM2600d (Minolta, Japan) and the skin blood flow with Laser Doppler Imaging-Periscan PIM II (Perimed AB, Sweden). The skin color and blood circulation of three groups (30-35 years, 36-40 years, 41-45 years) divided on age were analyzed by paired-t test and regression analysis. Results : The L* values of the skin were decreased and the a* values were increased significantly with age. This means that the more age increase, the more the skin is dark and red. But the skin blood flow was not significantly different with age and skin color. Conclusions : In the oriental medicine, It was reported that the face of the female over 35 years is changed gradually haggard and the blood circulation is decreased. In our study, the blood circulation was not changed and the skin color was dark and red with increasing the age. We think this symptom resulted from the better nutrition than the past, the change of the blood-quality and this changes were too sensitive to be measured by Laser Doppler Imaging system.

  • PDF