Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition
Recent advancement in unsupervised and transfer learning methods of deep learning networks has seen a complete paradigm shift in machine learning. Inspired by the recent evolution of deep learning (DL) networks that demonstrates a proven pathway of addressing challenging dilemmas in various problem...
| Main Authors: | , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2016
|
| Online Access: | http://hdl.handle.net/20.500.11937/38384 |
| _version_ | 1848755306170941440 |
|---|---|
| author | Pathirage, C. Li, L. Liu, Wan-Quan Zhang, M. |
| author_facet | Pathirage, C. Li, L. Liu, Wan-Quan Zhang, M. |
| author_sort | Pathirage, C. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Recent advancement in unsupervised and transfer learning methods of deep learning networks has seen a complete paradigm shift in machine learning. Inspired by the recent evolution of deep learning (DL) networks that demonstrates a proven pathway of addressing challenging dilemmas in various problem domains, we propose a novel DL framework for expression-robust feature acquisition. The framework exploits the contributions of different colour components in different local face regions by recovering the neutral expression from various expressions. Furthermore, the framework rigorously de-noises a face with dynamic expressions in a progressive way thus it is termed as stacked face de-noising auto-encoders (SFDAE). The high-level expression-robust representations that are learnt via this framework will not only yield better reconstruction of neutral expression faces but also boost the performance of the subsequent LDA[1] classifier. The experimental results reveal the superiority of the proposed method to the existing works in terms of its generalization ability and the high recognition accuracy. |
| first_indexed | 2025-11-14T08:54:12Z |
| format | Conference Paper |
| id | curtin-20.500.11937-38384 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:54:12Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-383842017-09-13T15:34:03Z Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition Pathirage, C. Li, L. Liu, Wan-Quan Zhang, M. Recent advancement in unsupervised and transfer learning methods of deep learning networks has seen a complete paradigm shift in machine learning. Inspired by the recent evolution of deep learning (DL) networks that demonstrates a proven pathway of addressing challenging dilemmas in various problem domains, we propose a novel DL framework for expression-robust feature acquisition. The framework exploits the contributions of different colour components in different local face regions by recovering the neutral expression from various expressions. Furthermore, the framework rigorously de-noises a face with dynamic expressions in a progressive way thus it is termed as stacked face de-noising auto-encoders (SFDAE). The high-level expression-robust representations that are learnt via this framework will not only yield better reconstruction of neutral expression faces but also boost the performance of the subsequent LDA[1] classifier. The experimental results reveal the superiority of the proposed method to the existing works in terms of its generalization ability and the high recognition accuracy. 2016 Conference Paper http://hdl.handle.net/20.500.11937/38384 10.1109/DICTA.2015.7371310 restricted |
| spellingShingle | Pathirage, C. Li, L. Liu, Wan-Quan Zhang, M. Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title | Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title_full | Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title_fullStr | Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title_full_unstemmed | Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title_short | Stacked Face De-Noising Auto Encoders for Expression-Robust Face Recognition |
| title_sort | stacked face de-noising auto encoders for expression-robust face recognition |
| url | http://hdl.handle.net/20.500.11937/38384 |