國立虎尾科技大學 |

Facial Attributes Analysis and Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Facial Attributes Analysis and Applications./
Author:	Liu, Xudong.
Description:	1 online resource (58 pages)
Notes:	Source: Masters Abstracts International, Volume: 58-01.
Contained By:	Masters Abstracts International58-01(E).
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780438322042

Facial Attributes Analysis and Applications.
Liu, Xudong.

Facial Attributes Analysis and Applications. - 1 online resource (58 pages)

Source: Masters Abstracts International, Volume: 58-01.

Thesis (M.S.)--West Virginia University, 2018.

Includes bibliographical references

Facial attributes are one of the most powerful descriptors for personality attribution. In the area of computer vision, researchers have worked on the extraction and use of attributes in face recognition. Facial attribute recognition is conventionally computed from a single image. In practice, it is quite common to capture multiple still images for each subject or to acquire a video of a subject with a number of image frames. Thus it is not rare to encounter the situation of having multiple still images or video frames of the same subject. Then it is quite natural to request a unique set of attributes about the subject given multiple face images. Naturally, how to compute the attributes given multiple images of the same subject?

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438322042Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Facial Attributes Analysis and Applications.
LDR:03057ntm a2200349Ki 4500 001 918424
005 20181114145236.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438322042
035 $a (MiAaPQ)AAI10845427
035 $a (MiAaPQ)wvumasters:10669
035 $a AAI10845427
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Liu, Xudong. $3 1186547
245 1 0 $a Facial Attributes Analysis and Applications.
264 0 $c 2018
300 $a 1 online resource (58 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 58-01.
500 $a Adviser: Guodong Guo.
502 $a Thesis (M.S.)--West Virginia University, 2018.
504 $a Includes bibliographical references
520 $a Facial attributes are one of the most powerful descriptors for personality attribution. In the area of computer vision, researchers have worked on the extraction and use of attributes in face recognition. Facial attribute recognition is conventionally computed from a single image. In practice, it is quite common to capture multiple still images for each subject or to acquire a video of a subject with a number of image frames. Thus it is not rare to encounter the situation of having multiple still images or video frames of the same subject. Then it is quite natural to request a unique set of attributes about the subject given multiple face images. Naturally, how to compute the attributes given multiple images of the same subject?
520 $a Firstly, we explore whether the inconsistency exists among the attributes computed from multiple face images of the same subject. The inconsistency can be caused by the variations in images, such as the face image quality changes. Then we develop methods in view of probabilistic confidence and image quality to address the inconsistency. Experimental results show that the proposed methods can handle facial attribute estimation on either multiple still images or video frames, and can correct the incorrectly annotated labels.
520 $a In addition, by computing the correlation between the facial attributes and the beauty score, we developed an application about mining semantic descriptions from facial attributes for beauty understanding. The facial beauty description is constructed from facial attributes. This is a totally data-driven method to address facial beauty instead of the psychology study. After analyzing beauty features, we adopt these features to the original facial images for testing the beauty difference. Experimental results indicate that the beauty semantics are reasonable and beneficial for the beauty modification.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a West Virginia University. $b Statler College of Engineering & Mineral Resources. $3 1148504
773 0 $t Masters Abstracts International $g 58-01(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10845427 $z click for full text (PQDT)