DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Jun Mo | - |
dc.contributor.advisor | 김준모 | - |
dc.contributor.author | Yim, Jun Ho | - |
dc.contributor.author | 임준호 | - |
dc.date.accessioned | 2016-05-03T19:37:51Z | - |
dc.date.available | 2016-05-03T19:37:51Z | - |
dc.date.issued | 2015 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=608545&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/206782 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학과, 2015.2 ,[vi, 31 p. :] | - |
dc.description.abstract | Face recognition under viewpoint and illumination changes is a difficult problem, so many researchers have tried to solve this problem by producing the pose- and illumination- invariant feature. Zhu et al. changed all arbitrary pose and illumination images to the frontal view image to use for the invariant feature. In this scheme, preserving identity while rotating pose image is a crucial issue. This paper proposes a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity. The target pose can be controlled by the user`s intention. This novel type of multi-task model significantly improves identity preservation over the single task model. By using all the synthesized controlled pose images, called Controlled Pose Image (CPI), for the pose- illumination- invariant feature and voting among the multiple face recognition results, we clearly outperform the state-of-the-art algorithms by more than 46% on the MultiPIE dataset. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | DNN | - |
dc.subject | Face Recognition | - |
dc.subject | Neural Network | - |
dc.subject | CNN | - |
dc.subject | 신경망 | - |
dc.subject | 신경망 학습 | - |
dc.subject | 얼굴인식 | - |
dc.title | Deep neural network for pose- and illumination- invariant face recognition | - |
dc.title.alternative | 포즈와 조명 변화에 강인한 딥러닝 기반 얼굴인식 기법에 대한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학과, | - |
dc.contributor.localauthor | Kim, Jun Mo | - |
dc.contributor.localauthor | 김준모 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.