지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 대한산업공학회 Industrial Engineering & Management Systems Industrial Engineering & Management Systems Vol.24 No.1
- 발행연도
- 2025.3
- 수록면
- 21 - 28 (8page)
- DOI
- 10.7232/iems.2025.24.1.021
이용수
초록· 키워드
오류제보하기
In recent years, image-generation technology has been successfully applied in the fashion industry. Previous studies have focused on the generation of fashion images that specify the clothes and poses of the person in the image or the changing of the clothes and poses of existing images. However, images were not generated with consideration given to attributes such as gender or height. To adapt image generation to real-world services, it is essential to generate images based on such user attributes. Consequently, in this study we generated images by utilizing the data of an actual fashion coordination site—that is, WEAR operated by ZOZO, Inc—with consideration given to attributes such as the gender, and height of the person in the image and an evaluation index of the image called the “number of likes”. First, a class label for each image was created based on the attribute information of the person in the image and evaluation of the image. By applying the created class label to the conditional part of the conditional StyleGAN2-ADA model and learning its parameters, it was possible to generate a “highly rated image” that was likely to be evaluated many times considering the attributes of the person in the image. Furthermore, visual inspection was conducted to evaluate whether an image with the specified attribute was actually generated, and image classification using EfficientNet V2 was performed to confirm whether a “highly evaluated image” had been generated.
목차
ABSTRACT
1. INTRODUCTION
2. RELATED WORK
3. CREATION OF CLASS LABELS
4. EXPERIMENTS
5. DISCUSSIONS
6. CONCLUSION AND FUTURE WORKS
REFERENCES
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
An Effective Method for Generating Color Images Using Genetic Algorithm
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2019 .06
-
Development of a Place Image Analysis Algorithm through Image Crawling and Deep-Learning
한국통신학회 학술대회논문집
2020 .11
-
영상 분할을 이용한 영상 전송 시스템에 대한 연구
반도체디스플레이기술학회지
2016 .01
-
Conditional GAN과 Mask R-CNN 기반의 Image-to-Image Translation을 이용한 차량 이미지 생성
한국통신학회 학술대회논문집
2019 .11
-
SinGAN을 이용한 Paint to Image 스타일 변환 구현
대한전자공학회 학술대회
2020 .08
-
Simulation of Filter Application for Segmentation of Medical Images
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2018 .06
-
Digital Image Quality Assessment Based on Standard Normal Deviation
International JOURNAL OF CONTENTS
2015 .06
-
영상 영역에 따른 카메라 모델 판별 성능 영향 분석
대한전자공학회 학술대회
2019 .11
-
Convolutional LSTM 모델을 이용한 인장편 특성 추정 방법
한국컴퓨터정보학회논문지
2018 .11
-
Image Generation Using Extremely Compressed Image
대한전자공학회 학술대회
2022 .06
-
라벨링 전처리를 위한 블러이미지 필터링 시스템 개발
한국자동차공학회 춘계학술대회
2024 .06
-
Infrared image generation based on Conditional Generative Adversarial Networks
한국지능정보시스템학회 학술대회논문집
2021 .12
-
CNN 이용 시 분류정확도를 향상시키기 위한 건축이미지 검색 방법
대한건축학회논문집
2020 .09
-
유의미한 숫자 포함 이미지의 대량 생성을 위한 딥러닝 기반 시스템
전기학회논문지
2020 .12
-
Generation of Highlight Free Image from Single Low Dynamic Range Image
한국통신학회 학술대회논문집
2017 .06
-
Conditional GAN 기반의 Image-to-Image Translation을 응용한 스케치 이미지 생성 방법
Proceedings of KIIT Conference
2019 .06
-
Image to Image Translation 기반의 안저 의료영상의 병변 위변조에 관한 연구
한국통신학회 학술대회논문집
2020 .08
-
Design and Implementation of High-Resolution Integral Imaging Display System using Expanded Depth Image
International JOURNAL OF CONTENTS
2018 .09
-
High Spatial Resolution Satellite Image Simulation Based on 3D Data and Existing Images
한국측량학회지
2016 .04
-
장소를 인식하는 이미지 평가항목에 대한 중요도 분석
한국농촌건축학회논문집
2022 .08
이 논문의 저자 정보
최근 본 자료
댓글(0)
0