[논문]딥러닝을 이용한 사용자 피부색 기반 파운데이션 색상 추천 기법 연구

정민욱; 김현지; 곽채원; 오유수

doi:10.9717/kmms.2022.25.9.1367

[국내논문] 딥러닝을 이용한 사용자 피부색 기반 파운데이션 색상 추천 기법 연구
A Study On User Skin Color-Based Foundation Color Recommendation Method Using Deep Learning 원문보기

멀티미디어학회논문지 = Journal of Korea Multimedia Society, v.25 no.9, 2022년, pp.1367 - 1374

정민욱 (School of Artificial Intelligence, Daegu University) , 김현지 (School of Artificial Intelligence, Daegu University) , 곽채원 (School of Computer Information Engineering, Daegu University) , 오유수 (School of Artificial Intelligence, Daegu University)

Abstract ▼ AI-Helper

In this paper, we propose an automatic cosmetic foundation recommendation system that suggests a good foundation product based on the user's skin color. The proposed system receives and preprocesses user images and detects skin color with OpenCV and machine learning algorithms. The system then compares the performance of the training model using XGBoost, Gradient Boost, Random Forest, and Adaptive Boost (AdaBoost), based on 550 datasets collected as essential bestsellers in the United States. Based on the comparison results, this paper implements a recommendation system using the highest performing machine learning model. As a result of the experiment, our system can effectively recommend a suitable skin color foundation. Thus, our system model is 98% accurate. Furthermore, our system can reduce the selection trials of foundations against the user's skin color. It can also save time in selecting foundations.

주제어

표/그림 (8)

그림 Fig. 1. Diagram of the foundation recommendation system.
그림 Fig. 2. Skin detection area.
그림 Fig. 3. Graph of results learned using RandomForest, Adaboost, Xgboost, Gradient Boosting.
그림 Fig. 4. Graph of results learned using RandomForest, Adaboost, Xgboost, Gradient Boosting.
그림 Fig. 5. Graph of results learned using RandomForest, Adaboost, Xgboost, Gradient Boosting.
그림 Fig. 6. Face detection results of various images.
표 Table 1. Comparison of accuracy values by feature value and algorithm(H : Hue, S : Saturation, V : Value, L : Luminosity, Hex : Hexadecimal).
표 Table 2. Detected user's skin color and recommendation foundation.

참고문헌 (18)

H. Shin, Y. Lim, Y. Hong, J. Lim, J. Park, H. Lee, et al., "Design and Implementation of Cosmetic Recommendation System Using Machine Learning in Social Media Environment," The Korean Content Society General Conference Euromonitor International, pp. 289-290, 2021.
Euromonitor International(2021), https://go.euromonitor.com/white-paper-EC-2021-Top-10-Global-Consumer-Trends.html (accessed January 19, 2021).
Y. Yoon and H. Park, "Automatic Recommendation of Foundation Color Based on User's Skin Color," Korean Institute of Intelligent Systems, Vol. 29, No. 4, pp. 280-284, 2019.

상세보기
C. Tianqi and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," arXiv Preprint, arXiv:1603.02754, 2016.
J. Lee, A Study on Recent Boosting Methods, Department of Applied Statistics Graduate School of Konkuk University, 2020.
G. Choi, J. Park, and H. Nguyen, "Feature Selection Algorithm using Random Forest to Diagnose Cancer," International Journal of Internet, Broadcasting and Communication, Vo. 1, No. 1, pp. 10-15, 2009.
W. Lee, J. Kim, and B. Lee, "Real-Time Face Detection and Tracking Using the AdaBoost Algorithm," Journal of Korea Multimedia Society, Vol. 9, No. 10, pp. 1266-1275, 2006.
K. Zhang, Z. Zhang, Z. Li, and Y. Qiao, "Joint Face Detection and Alignment using Multitask Cascaded Convolutional Networks," IEEE Signal P rocessing Letters, Vol. 23, Issue 10, pp. 1499-1503, 2016.

상세보기
S. Kim, E. Kim, and Y. Kim, "System for Recommendation of Cosmetics through Fuzzy Inference and Emotional Dictionary," Korean Institute of Intelligent Systems, Vol. 27, No. 3, pp. 253-260, 2017.

상세보기
W. Yun, D.-H. Seo, S. Min, H. Nam, "Breast Cancer Classification using RandomForest and XGBoost," Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp. 113-114, 2021.
H. Kim, W. Shin, D. Shin, H. Kim, and H. Kim, "Development of a Cosmetic Recommendation System Utilizing Customer's Characteristic Information," Information Systems Review, Vol. 23, No. 4, pp. 69-84, 2021.
E. Park, M. Lee, M. Jung, D. Park, and Y. Moon, "Male Cosmetics Customized Recommendation and Information Provision Service," Proceedings of the Korean Society of Computer Information Conference, Vol. 29, No. 1, pp. 353-354, 2021.
Makeup Shades Dataset l Kaggle, https://www.kaggle.com/datasets/shivamb/makeupshades-dataset (Accessed on January 19, 2021).
Y. Han and I. Jo, "Advertisement Click Prediction Using Early Stop Based on XGBoost," The Journal of Korean Institute of Communications and Information Sciences, Vol. 46, No. 6, pp. 993-1000, 2021.

상세보기
A. Kwon, You Have Chosen a Random Cannon, Master's Degree in Korea Graduated from Inha University, 2013.
P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and P attern Recognition (CVPR 2001), Vol. 1. pp. 511-518, 2001.
Pixabay, https://pixabay.com/ (Accessed on July 1, 2022).
K. Kang, "Decision Tree Techniques with Feature Reduction for Network Anomaly Detection," Journal of The Korea Institute of Information Security and Cryptology (JKIISC), Vol. 29, No. 4, pp. 795-805, 2019.

원문보기 상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증