東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Exploiting space-time statistics of ...

Dedeoglu, Goksel.

Linked to FindBook

Google Book

Amazon

博客來

Exploiting space-time statistics of videos for face "Hallucination".

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Exploiting space-time statistics of videos for face "Hallucination"./
Author:	Dedeoglu, Goksel.
Description:	126 p.
Notes:	Adviser: Takeo Kanade.
Contained By:	Dissertation Abstracts International68-06B.
Subject:	Artificial Intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3270860
ISBN:	9780549086611

Exploiting space-time statistics of videos for face "Hallucination".
Dedeoglu, Goksel.

Exploiting space-time statistics of videos for face "Hallucination". - 126 p.

Adviser: Takeo Kanade.

Thesis (Ph.D.)--Carnegie Mellon University, 2007.

Face "Hallucination" aims to recover high quality, high-resolution images of human faces from low-resolution, blurred, and degraded images or video. This thesis presents person-specific solutions to this problem through careful exploitation of space (image) and space-time (video) models. The results demonstrate accurate restoration of facial details, with resolution enhancements upto a scaling factor of 16.

ISBN: 9780549086611Subjects--Topical Terms:

769149
Artificial Intelligence.

Exploiting space-time statistics of videos for face "Hallucination".
LDR:03301nam 2200313 a 45 001 958922
005 20110704
008 110704s2007 ||||||||||||||||| ||eng d
020 $a 9780549086611
035 $a (UMI)AAI3270860
035 $a AAI3270860
040 $a UMI $c UMI
100 1 $a Dedeoglu, Goksel. $3 1282388
245 1 0 $a Exploiting space-time statistics of videos for face "Hallucination".
300 $a 126 p.
500 $a Adviser: Takeo Kanade.
500 $a Source: Dissertation Abstracts International, Volume: 68-06, Section: B, page: 4108.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2007.
520 $a Face "Hallucination" aims to recover high quality, high-resolution images of human faces from low-resolution, blurred, and degraded images or video. This thesis presents person-specific solutions to this problem through careful exploitation of space (image) and space-time (video) models. The results demonstrate accurate restoration of facial details, with resolution enhancements upto a scaling factor of 16.
520 $a The algorithms proposed in this thesis follow the analysis-by-synthesis paradigm; they explain the observed (low-resolution) data by fitting a (high-resolution) model. In this context, the first contribution is the discovery of a scaling-induced bias that plagues most model-to-image (or image-to-image) fitting algorithms. It was found that models and observations should be treated asymmetrically , both to formulate an unbiased objective function and to derive an accurate optimization algorithm. This asymmetry is most relevant to Face Hallucination: when applied to the popular Active Appearance Model, it leads to a novel face tracking and reconstruction algorithm that is significantly more accurate than state-of-the-art methods. The analysis also reveals the inherent trade-off between computational efficiency and estimation accuracy in low-resolution regimes.
520 $a The second contribution is a statistical generative model of face videos. By treating a video as a composition of space-time patches, this model efficiently encodes the temporal dynamics of complex visual phenomena such as eye-blinks and the occlusion or appearance of teeth. The same representation is also used to define a data-driven prior on a three-dimensional Markov Random Field in space and time. Experimental results demonstrate that temporal representation and reasoning about facial expressions improves robustness by regularizing the Face Hallucination problem.
520 $a The final contribution is an approximate compensation scheme against illumination effects. It is observed that distinct illumination subspaces of a face (each coming from a different pose and expression) still exhibit similar variation with respect to illumination. This motivates augmenting the video model with a low-dimensional illumination subspace, whose parameters are estimated jointly with high-resolution face details. Successful Face Hallucinations beyond the lighting conditions of the training videos are reported.
590 $a School code: 0041.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Engineering, Robotics. $3 1018454
690 $a 0771
690 $a 0800
710 2 $a Carnegie Mellon University. $3 1018096
773 0 $t Dissertation Abstracts International $g 68-06B.
790 $a 0041
790 1 0 $a Kanade, Takeo, $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3270860