國立虎尾科技大學 |

Face Verification Using Domain Adaptation.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Face Verification Using Domain Adaptation./
作者:	Choksi, Aditi.
面頁冊數:	1 online resource (63 pages)
附註:	Source: Masters Abstracts International, Volume: 84-04.
Contained By:	Masters Abstracts International84-04.
標題:	Information science. -
電子資源:	click for full text (PQDT)
ISBN:	9798351474465

Face Verification Using Domain Adaptation.
Choksi, Aditi.

Face Verification Using Domain Adaptation. - 1 online resource (63 pages)

Source: Masters Abstracts International, Volume: 84-04.

Thesis (M.S.)--University of Maryland, Baltimore County, 2022.

Includes bibliographical references

Face verification is a one-to-one matching technique that involves comparing a pair of faces to determine if these faces correspond to a shared identity. Face verification is commonly used in biometric applications, including mobile computing, as well as law enforcement and surveillance applications. However, surveillance imagery is often blurry, whereas mobile phone portraits are often relatively clear. Moreover, commonly employed face datasets often contain imagery of faces in well-lit environments obtained from high definition videos which are unrealistically clear as compared to many use cases in the wild. Variation in image quality and lighting leads to substantial domain shift and performance degradation for deep face verification algorithms. Deep face verification techniques that are trained and tested on clear imagery are often unable to perform well in blurry and poorly lit environments. We present a novel approach using unsupervised domain adaptation in order to construct a model for face verification that is robust to variation in image clarity. Unsupervised domain adaptation techniques allow the model to be trained on labeled imagery from a source domain in combination with unlabeled imagery from the target domain in order to learn domain invariant feature representations. Our methodology incorporates a pre-trained Inception Resnet V1 into a Siamese Domain Invariant Feature Learning (Si-DIFL) meta-architecture. To the best of our knowledge, our proposed approach is the first to combine domain invariant feature learning with siamese networks, and is furthermore the first to employ this approach to the application of face verification. This experiment sheds light on the difficulty of the problem space of blurry face recognition, as well as the brittleness of present-day face-verification systems to variation in image quality. We demonstrate that domain adaptation using Si-DIFL is a viable approach toward improving the robustness and reducing the brittleness of deep face verification algorithms.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798351474465Subjects--Topical Terms:

561178
Information science.
Subjects--Index Terms:

Blurred face recognitionIndex Terms--Genre/Form:

554714
Electronic books.

Face Verification Using Domain Adaptation.
LDR:03379ntm a22003977 4500 001 1147223
005 20240909100729.5
006 m o d
007 cr bn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798351474465
035 $a (MiAaPQ)AAI29210532
035 $a AAI29210532
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Choksi, Aditi. $3 1472892
245 1 0 $a Face Verification Using Domain Adaptation.
264 0 $c 2022
300 $a 1 online resource (63 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: 84-04.
500 $a Advisor: Chapman, David.
502 $a Thesis (M.S.)--University of Maryland, Baltimore County, 2022.
504 $a Includes bibliographical references
520 $a Face verification is a one-to-one matching technique that involves comparing a pair of faces to determine if these faces correspond to a shared identity. Face verification is commonly used in biometric applications, including mobile computing, as well as law enforcement and surveillance applications. However, surveillance imagery is often blurry, whereas mobile phone portraits are often relatively clear. Moreover, commonly employed face datasets often contain imagery of faces in well-lit environments obtained from high definition videos which are unrealistically clear as compared to many use cases in the wild. Variation in image quality and lighting leads to substantial domain shift and performance degradation for deep face verification algorithms. Deep face verification techniques that are trained and tested on clear imagery are often unable to perform well in blurry and poorly lit environments. We present a novel approach using unsupervised domain adaptation in order to construct a model for face verification that is robust to variation in image clarity. Unsupervised domain adaptation techniques allow the model to be trained on labeled imagery from a source domain in combination with unlabeled imagery from the target domain in order to learn domain invariant feature representations. Our methodology incorporates a pre-trained Inception Resnet V1 into a Siamese Domain Invariant Feature Learning (Si-DIFL) meta-architecture. To the best of our knowledge, our proposed approach is the first to combine domain invariant feature learning with siamese networks, and is furthermore the first to employ this approach to the application of face verification. This experiment sheds light on the difficulty of the problem space of blurry face recognition, as well as the brittleness of present-day face-verification systems to variation in image quality. We demonstrate that domain adaptation using Si-DIFL is a viable approach toward improving the robustness and reducing the brittleness of deep face verification algorithms.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information science. $3 561178
650 4 $a Computer science. $3 573171
653 $a Blurred face recognition
653 $a Domain adaptation
653 $a Face verification
653 $a Neural networks
653 $a Siamese networks
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a University of Maryland, Baltimore County. $b Computer Science. $3 1179407
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 84-04.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29210532 $z click for full text (PQDT)