http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Nusrat Tasnim (검색결과 1 건)
- 무료
- 기관 내 무료
- 유료
-
Md. Mahbubul Islam,Nusrat Tasnim,Joong-Hwan Baek 한국정보통신학회 2021 2016 INTERNATIONAL CONFERENCE Vol.12 No.1
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.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
