A framework of enlarging face datasets used for makeup face analysis

Min-Chun Hu, Hsin Ting Wu, Li Yun Lo, Tse Yu Pan, Wen Huang Cheng, Kai Lung Hua, Tao Mei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There have been lots of research about face detection and face recognition. However, faces with makeup usually seriously affect the face recognition result. If we want to recognize the face with higher accuracy, it would be better to first know whether the input face is with makeup or not, and we can use corresponding makeup face or non-makeup face model to recognize it. Unfortunately, the current available datasets for face analysis do not include enough makeup and non-makeup image pairs of users. In this work, we propose a framework to efficiently increase pairs of makeup and non-makeup face images for the existing makeup face datasets. Patch-based features are extracted and support vector machine (SVM) is applied to classify whether a face image is with makeup. The technique of partial least squares (PLS) is then employed to authenticate whether a makeup photo and a non-makeup photo belong to the same person. By combining the makeup detection and the face authentication methods, we can successfully construct a larger face dataset that can be specifically used for applications of makeup face analysis.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages219-222
Number of pages4
ISBN (Electronic)9781509021789
DOIs
Publication statusPublished - 2016 Aug 16
Event2nd IEEE International Conference on Multimedia Big Data, BigMM 2016 - Taipei, Taiwan
Duration: 2016 Apr 202016 Apr 22

Publication series

NameProceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

Other

Other2nd IEEE International Conference on Multimedia Big Data, BigMM 2016
CountryTaiwan
CityTaipei
Period16-04-2016-04-22

Fingerprint

Face recognition
Authentication
Support vector machines

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Media Technology

Cite this

Hu, M-C., Wu, H. T., Lo, L. Y., Pan, T. Y., Cheng, W. H., Hua, K. L., & Mei, T. (2016). A framework of enlarging face datasets used for makeup face analysis. In Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016 (pp. 219-222). [7545025] (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigMM.2016.62
Hu, Min-Chun ; Wu, Hsin Ting ; Lo, Li Yun ; Pan, Tse Yu ; Cheng, Wen Huang ; Hua, Kai Lung ; Mei, Tao. / A framework of enlarging face datasets used for makeup face analysis. Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 219-222 (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016).
@inproceedings{bf9f7a2c63a44b918f491bbb1efd9e4d,
title = "A framework of enlarging face datasets used for makeup face analysis",
abstract = "There have been lots of research about face detection and face recognition. However, faces with makeup usually seriously affect the face recognition result. If we want to recognize the face with higher accuracy, it would be better to first know whether the input face is with makeup or not, and we can use corresponding makeup face or non-makeup face model to recognize it. Unfortunately, the current available datasets for face analysis do not include enough makeup and non-makeup image pairs of users. In this work, we propose a framework to efficiently increase pairs of makeup and non-makeup face images for the existing makeup face datasets. Patch-based features are extracted and support vector machine (SVM) is applied to classify whether a face image is with makeup. The technique of partial least squares (PLS) is then employed to authenticate whether a makeup photo and a non-makeup photo belong to the same person. By combining the makeup detection and the face authentication methods, we can successfully construct a larger face dataset that can be specifically used for applications of makeup face analysis.",
author = "Min-Chun Hu and Wu, {Hsin Ting} and Lo, {Li Yun} and Pan, {Tse Yu} and Cheng, {Wen Huang} and Hua, {Kai Lung} and Tao Mei",
year = "2016",
month = "8",
day = "16",
doi = "10.1109/BigMM.2016.62",
language = "English",
series = "Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "219--222",
booktitle = "Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016",
address = "United States",

}

Hu, M-C, Wu, HT, Lo, LY, Pan, TY, Cheng, WH, Hua, KL & Mei, T 2016, A framework of enlarging face datasets used for makeup face analysis. in Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016., 7545025, Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016, Institute of Electrical and Electronics Engineers Inc., pp. 219-222, 2nd IEEE International Conference on Multimedia Big Data, BigMM 2016, Taipei, Taiwan, 16-04-20. https://doi.org/10.1109/BigMM.2016.62

A framework of enlarging face datasets used for makeup face analysis. / Hu, Min-Chun; Wu, Hsin Ting; Lo, Li Yun; Pan, Tse Yu; Cheng, Wen Huang; Hua, Kai Lung; Mei, Tao.

Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 219-222 7545025 (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A framework of enlarging face datasets used for makeup face analysis

AU - Hu, Min-Chun

AU - Wu, Hsin Ting

AU - Lo, Li Yun

AU - Pan, Tse Yu

AU - Cheng, Wen Huang

AU - Hua, Kai Lung

AU - Mei, Tao

PY - 2016/8/16

Y1 - 2016/8/16

N2 - There have been lots of research about face detection and face recognition. However, faces with makeup usually seriously affect the face recognition result. If we want to recognize the face with higher accuracy, it would be better to first know whether the input face is with makeup or not, and we can use corresponding makeup face or non-makeup face model to recognize it. Unfortunately, the current available datasets for face analysis do not include enough makeup and non-makeup image pairs of users. In this work, we propose a framework to efficiently increase pairs of makeup and non-makeup face images for the existing makeup face datasets. Patch-based features are extracted and support vector machine (SVM) is applied to classify whether a face image is with makeup. The technique of partial least squares (PLS) is then employed to authenticate whether a makeup photo and a non-makeup photo belong to the same person. By combining the makeup detection and the face authentication methods, we can successfully construct a larger face dataset that can be specifically used for applications of makeup face analysis.

AB - There have been lots of research about face detection and face recognition. However, faces with makeup usually seriously affect the face recognition result. If we want to recognize the face with higher accuracy, it would be better to first know whether the input face is with makeup or not, and we can use corresponding makeup face or non-makeup face model to recognize it. Unfortunately, the current available datasets for face analysis do not include enough makeup and non-makeup image pairs of users. In this work, we propose a framework to efficiently increase pairs of makeup and non-makeup face images for the existing makeup face datasets. Patch-based features are extracted and support vector machine (SVM) is applied to classify whether a face image is with makeup. The technique of partial least squares (PLS) is then employed to authenticate whether a makeup photo and a non-makeup photo belong to the same person. By combining the makeup detection and the face authentication methods, we can successfully construct a larger face dataset that can be specifically used for applications of makeup face analysis.

UR - http://www.scopus.com/inward/record.url?scp=84987678181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987678181&partnerID=8YFLogxK

U2 - 10.1109/BigMM.2016.62

DO - 10.1109/BigMM.2016.62

M3 - Conference contribution

T3 - Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

SP - 219

EP - 222

BT - Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hu M-C, Wu HT, Lo LY, Pan TY, Cheng WH, Hua KL et al. A framework of enlarging face datasets used for makeup face analysis. In Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 219-222. 7545025. (Proceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016). https://doi.org/10.1109/BigMM.2016.62