Thermal infrared exploitation for 3D face reconstruction
| Autor: | Bernard Abayowa |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
Computer science
business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing Iterative reconstruction Facial recognition system Luminance GeneralLiterature_MISCELLANEOUS Urban search and rescue Computer vision Artificial intelligence Invariant (mathematics) business Search and rescue ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | SPIE Proceedings. |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.818720 |
| Popis: | Despite the advances in face recognition research, current face recognition systems are still not accurate or robust enough to be deployed in uncontrolled environments. The existence of a pose and illumination invariant face recognition system is still lacking. This research exploits the relationship between thermal infrared and visible imagery, to estimate 3D face with visible texture from infrared imagery. The relationship between visible and thermal infrared texture is learned using kernel canonical correlation analysis(KCCA), and then a 3D modeler is used to estimate the geometric structure from predicted visual imagery. This research will find it's application in uncontrolled environments where illumination and pose invariant identification or tracking is required at long range such as urban search and rescue (Amber alert, missing dementia patient), and manhunt scenarios. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|