國立虎尾科技大學 |

Machine Learning Approaches to Human Body Shape Analysis.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Machine Learning Approaches to Human Body Shape Analysis./
作者:	Piccirilli, Marco.
面頁冊數:	1 online resource (247 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
Contained By:	Dissertation Abstracts International79-09B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355939194

Machine Learning Approaches to Human Body Shape Analysis.
Piccirilli, Marco.

Machine Learning Approaches to Human Body Shape Analysis. - 1 online resource (247 pages)

Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.

Thesis (Ph.D.)--West Virginia University, 2018.

Includes bibliographical references

Soft biometrics, biomedical sciences, and many other fields of study pay particular attention to the study of the geometric description of the human body, and its variations. Although multiple contributions, the interest is particularly high given the non-rigid nature of the human body, capable of assuming different poses, and numerous shapes due to variable body composition. Unfortunately, a well-known costly requirement in data-driven machine learning, and particularly in the human-based analysis, is the availability of data, in the form of geometric information (body measurements) with related vision information (natural images, 3D mesh, etc.). We introduce a computer graphics framework able to generate thousands of synthetic human body meshes, representing a population of individuals with stratified information: gender, Body Fat Percentage (BFP), anthropometric measurements, and pose. This contribution permits an extensive analysis of different bodies in different poses, avoiding the demanding, and expensive acquisition process. We design a virtual environment able to take advantage of the generated bodies, to infer the body surface area (BSA) from a single view. The framework permits to simulate the acquisition process of newly introduced RGB-D devices disentangling different noise components (sensor noise, optical distortion, body part occlusions). Common geometric descriptors in soft biometric, as well as in biomedical sciences, are based on body measurements. Unfortunately, as we prove, these descriptors are not pose invariant, constraining the usability in controlled scenarios. We introduce a differential geometry approach assuming body pose variations as isometric transformations of the body surface, and body composition changes covariant to the body surface area. This setting permits the use of the Laplace-Beltrami operator on the 2D body manifold, describing the body with a compact, efficient, and pose invariant representation. We design a neural network architecture able to infer important body semantics from spectral descriptors, closing the gap between abstract spectral features, and traditional measurement-based indices. Studying the manifold of body shapes, we propose an innovative generative adversarial model able to learn the body shapes. The method permits to generate new bodies with unseen geometries as a walk on the latent space, constituting a significant advantage over traditional generative methods.

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

Mode of access: World Wide Web

ISBN: 9780355939194Subjects--Topical Terms:

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

554714
Electronic books.

Machine Learning Approaches to Human Body Shape Analysis.
LDR:03719ntm a2200349Ki 4500 001 918403
005 20181114145236.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355939194
035 $a (MiAaPQ)AAI10811065
035 $a (MiAaPQ)wvu:11973
035 $a AAI10811065
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Piccirilli, Marco. $3 1192719
245 1 0 $a Machine Learning Approaches to Human Body Shape Analysis.
264 0 $c 2018
300 $a 1 online resource (247 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: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
500 $a Advisers: Donald Adjeroh; Gianfranco Doretto.
502 $a Thesis (Ph.D.)--West Virginia University, 2018.
504 $a Includes bibliographical references
520 $a Soft biometrics, biomedical sciences, and many other fields of study pay particular attention to the study of the geometric description of the human body, and its variations. Although multiple contributions, the interest is particularly high given the non-rigid nature of the human body, capable of assuming different poses, and numerous shapes due to variable body composition. Unfortunately, a well-known costly requirement in data-driven machine learning, and particularly in the human-based analysis, is the availability of data, in the form of geometric information (body measurements) with related vision information (natural images, 3D mesh, etc.). We introduce a computer graphics framework able to generate thousands of synthetic human body meshes, representing a population of individuals with stratified information: gender, Body Fat Percentage (BFP), anthropometric measurements, and pose. This contribution permits an extensive analysis of different bodies in different poses, avoiding the demanding, and expensive acquisition process. We design a virtual environment able to take advantage of the generated bodies, to infer the body surface area (BSA) from a single view. The framework permits to simulate the acquisition process of newly introduced RGB-D devices disentangling different noise components (sensor noise, optical distortion, body part occlusions). Common geometric descriptors in soft biometric, as well as in biomedical sciences, are based on body measurements. Unfortunately, as we prove, these descriptors are not pose invariant, constraining the usability in controlled scenarios. We introduce a differential geometry approach assuming body pose variations as isometric transformations of the body surface, and body composition changes covariant to the body surface area. This setting permits the use of the Laplace-Beltrami operator on the 2D body manifold, describing the body with a compact, efficient, and pose invariant representation. We design a neural network architecture able to infer important body semantics from spectral descriptors, closing the gap between abstract spectral features, and traditional measurement-based indices. Studying the manifold of body shapes, we propose an innovative generative adversarial model able to learn the body shapes. The method permits to generate new bodies with unseen geometries as a walk on the latent space, constituting a significant advantage over traditional generative methods.
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
650 4 $a Electrical engineering. $3 596380
650 4 $a Medicine. $3 644133
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0544
690 $a 0564
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 Dissertation Abstracts International $g 79-09B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10811065 $z click for full text (PQDT)