메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Md. Mahbubul Islam (Korea Aerospace University) Nusrat Tasnim (Korea Aerospace University) Joong-Hwan Baek (Korea Aerospace University)
저널정보
한국정보통신학회 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2020 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING Vo.12 No.1
발행연도
2021.2
수록면
68 - 71 (4page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
In this study, authors aimed to predict the gender of a customer with face mask to manage the customer data, targeted advertisement, and future of retail. Amid the COVID-19 pandemic situation, a customer must wear a face mask, avoid contacts with store staffs and should stay for short period of times while shopping. Smart store can meet the requirements by knowing the customer gender to find the right item. Predicting gender from faces with mask is a perplexing task due to two main reasons: 1) the lack of large benchmark datasets of masked faces, and 2) the deficiency of facial cues from the masked regions. Faces in the unconstraint environment have various orientations and occlusion degrees, where no less than one part of each face is occluded by mask. The traditional machine learning approaches are suffering in performance with the heterogeneity of the images in the non-benchmark dataset. This research proposes an automatic gender prediction system deploying deep learning networks; GoogleNet and ResNet50 those are pretrained with huge amount of image data. The extensive experiments demonstrate a noteworthy prediction accuracy (83%) even though the amount of available masked face data is very limited. Furthermore, this is the first work of gender prediction with the real masked face dataset heretofore.

목차

Abstract
I. INTRODUCTION
II. SYSTEM MODEL AND METHODS
III. RESULTS
IV. DISCUSSION AND CONCLUSIONS
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2021-004-001552650