Face recognition based on image sets
In this thesis, we study the problem of face recognition based on image sets. The main objective of our work is to develop set-based distance metrics that are able to measure the similarity between image sets, rather than conventional distance metrics that can only measure the distance between sampl...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/61822 |
| _version_ | 1811687920071868416 |
|---|---|
| author | Huang, Likun |
| author2 | Tan Yap Peng |
| author_facet | Tan Yap Peng Huang, Likun |
| author_sort | Huang, Likun |
| collection | NTU |
| description | In this thesis, we study the problem of face recognition based on image sets. The main objective of our work is to develop set-based distance metrics that are able to measure the similarity between image sets, rather than conventional distance metrics that can only measure the distance between samples. The face images obtained from real-life impose great challenges to the conventional face recognition systems. Large variations in appearances and various imperfections such as occlusions and misalignments in the face images severely degrade the recognition performance. One possible solution is to utilize more face images for each person, e.g., a collection of photos from personal galleries or frames extracted from a video clip. Under such circumstances, the face recognition task becomes the process of modelling and matching image sets. Our investigation then focuses on developing appropriate models and set-based distance metrics for representing different image sets. |
| first_indexed | 2024-10-01T05:23:58Z |
| format | Thesis |
| id | ntu-10356/61822 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:23:58Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | ntu-10356/618222023-07-04T17:14:08Z Face recognition based on image sets Huang, Likun Tan Yap Peng School of Electrical and Electronic Engineering DRNTU::Engineering::Bioengineering In this thesis, we study the problem of face recognition based on image sets. The main objective of our work is to develop set-based distance metrics that are able to measure the similarity between image sets, rather than conventional distance metrics that can only measure the distance between samples. The face images obtained from real-life impose great challenges to the conventional face recognition systems. Large variations in appearances and various imperfections such as occlusions and misalignments in the face images severely degrade the recognition performance. One possible solution is to utilize more face images for each person, e.g., a collection of photos from personal galleries or frames extracted from a video clip. Under such circumstances, the face recognition task becomes the process of modelling and matching image sets. Our investigation then focuses on developing appropriate models and set-based distance metrics for representing different image sets. DOCTOR OF PHILOSOPHY (EEE) 2014-11-04T01:45:57Z 2014-11-04T01:45:57Z 2014 2014 Thesis Huang, L. (2014). Face recognition based on image sets. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/61822 10.32657/10356/61822 en 168 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Bioengineering Huang, Likun Face recognition based on image sets |
| title | Face recognition based on image sets |
| title_full | Face recognition based on image sets |
| title_fullStr | Face recognition based on image sets |
| title_full_unstemmed | Face recognition based on image sets |
| title_short | Face recognition based on image sets |
| title_sort | face recognition based on image sets |
| topic | DRNTU::Engineering::Bioengineering |
| url | https://hdl.handle.net/10356/61822 |
| work_keys_str_mv | AT huanglikun facerecognitionbasedonimagesets |