SegTex: A Large Scale Synthetic Face Dataset for Face Recognition
Face recognition remains challenged by data limitations in both scale and diversity, coupled with the ethical dilemmas of using images without the subjects’ consent. To address these issues, this paper presents the SegTex framework, a cutting-edge method for generating synthetic face data...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10328591/ |
| _version_ | 1797321110485729280 |
|---|---|
| author | Laudwika Ambardi Sungeun Hong In Kyu Park |
| author_facet | Laudwika Ambardi Sungeun Hong In Kyu Park |
| author_sort | Laudwika Ambardi |
| collection | DOAJ |
| description | Face recognition remains challenged by data limitations in both scale and diversity, coupled with the ethical dilemmas of using images without the subjects’ consent. To address these issues, this paper presents the SegTex framework, a cutting-edge method for generating synthetic face datasets by converting Segmentation maps into Textured images. Using the CelebAHQ-Mask dataset for segmentation maps and extracting facial features from the CelebAMask-HQ dataset, the SegTex method efficiently creates varied synthetic facial characteristics. This approach not only sidesteps the need for real-world data collection but also offers a rich and diverse dataset, essential for improving face recognition algorithm performance. In our experiments, models trained on the SegTex-generated dataset displayed superior performance metrics when compared to those trained on conventional datasets, underscoring the practical utility of our method. This robust performance, combined with the ethical advantages of synthetic data generation, ensures our approach holds significant importance in the field of face recognition. |
| first_indexed | 2024-03-08T04:52:48Z |
| format | Article |
| id | doaj.art-abb31b97578f49bbb8290db3f3194d53 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T04:52:48Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-abb31b97578f49bbb8290db3f3194d532024-02-08T00:01:31ZengIEEEIEEE Access2169-35362023-01-011113193913194910.1109/ACCESS.2023.333640510328591SegTex: A Large Scale Synthetic Face Dataset for Face RecognitionLaudwika Ambardi0https://orcid.org/0000-0002-7892-8066Sungeun Hong1https://orcid.org/0000-0003-1774-9168In Kyu Park2https://orcid.org/0000-0003-4774-7841Department of Electrical and Computer Engineering, Inha University, Incheon, South KoreaDepartment of Immersive Media Engineering, Sungkyunkwan University, Seoul, South KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon, South KoreaFace recognition remains challenged by data limitations in both scale and diversity, coupled with the ethical dilemmas of using images without the subjects’ consent. To address these issues, this paper presents the SegTex framework, a cutting-edge method for generating synthetic face datasets by converting Segmentation maps into Textured images. Using the CelebAHQ-Mask dataset for segmentation maps and extracting facial features from the CelebAMask-HQ dataset, the SegTex method efficiently creates varied synthetic facial characteristics. This approach not only sidesteps the need for real-world data collection but also offers a rich and diverse dataset, essential for improving face recognition algorithm performance. In our experiments, models trained on the SegTex-generated dataset displayed superior performance metrics when compared to those trained on conventional datasets, underscoring the practical utility of our method. This robust performance, combined with the ethical advantages of synthetic data generation, ensures our approach holds significant importance in the field of face recognition.https://ieeexplore.ieee.org/document/10328591/Face synthesissynthetic datasetface recognition |
| spellingShingle | Laudwika Ambardi Sungeun Hong In Kyu Park SegTex: A Large Scale Synthetic Face Dataset for Face Recognition IEEE Access Face synthesis synthetic dataset face recognition |
| title | SegTex: A Large Scale Synthetic Face Dataset for Face Recognition |
| title_full | SegTex: A Large Scale Synthetic Face Dataset for Face Recognition |
| title_fullStr | SegTex: A Large Scale Synthetic Face Dataset for Face Recognition |
| title_full_unstemmed | SegTex: A Large Scale Synthetic Face Dataset for Face Recognition |
| title_short | SegTex: A Large Scale Synthetic Face Dataset for Face Recognition |
| title_sort | segtex a large scale synthetic face dataset for face recognition |
| topic | Face synthesis synthetic dataset face recognition |
| url | https://ieeexplore.ieee.org/document/10328591/ |
| work_keys_str_mv | AT laudwikaambardi segtexalargescalesyntheticfacedatasetforfacerecognition AT sungeunhong segtexalargescalesyntheticfacedatasetforfacerecognition AT inkyupark segtexalargescalesyntheticfacedatasetforfacerecognition |