國立虎尾科技大學 |

Leveraging image manifolds for visual learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Leveraging image manifolds for visual learning./
作者:	Bakry, Amr M.
面頁冊數:	1 online resource (94 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-07(E), Section: B.
Contained By:	Dissertation Abstracts International78-07B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369605280

Leveraging image manifolds for visual learning.
Bakry, Amr M.

Leveraging image manifolds for visual learning. - 1 online resource (94 pages)

Source: Dissertation Abstracts International, Volume: 78-07(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

The field of computer vision has recently witnessed remarkable progress, due mainly to visual data availability and machine learning advances. Modeling the visual data is challenging due to several factors, such as loss of information while projecting 3D world to 2D plain, high dimensionality of the visual data, and existence of nuisance parameters such as occlusion, clutter, illumination and noise. In this dissertation, we focus on modeling the inter and intra image manifold variability.

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

Mode of access: World Wide Web

ISBN: 9781369605280Subjects--Topical Terms:

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

554714
Electronic books.

Leveraging image manifolds for visual learning.
LDR:03148ntm a2200373Ki 4500 001 909837
005 20180426091048.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369605280
035 $a (MiAaPQ)AAI10478534
035 $a (MiAaPQ)rutgersnb:7517
035 $a AAI10478534
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Bakry, Amr M. $3 1180805
245 1 0 $a Leveraging image manifolds for visual learning.
264 0 $c 2016
300 $a 1 online resource (94 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: 78-07(E), Section: B.
500 $a Adviser: Ahmed Elgammal.
502 $a Thesis (Ph.D.) $c Rutgers The State University of New Jersey - New Brunswick $d 2016.
504 $a Includes bibliographical references
520 $a The field of computer vision has recently witnessed remarkable progress, due mainly to visual data availability and machine learning advances. Modeling the visual data is challenging due to several factors, such as loss of information while projecting 3D world to 2D plain, high dimensionality of the visual data, and existence of nuisance parameters such as occlusion, clutter, illumination and noise. In this dissertation, we focus on modeling the inter and intra image manifold variability.
520 $a The dissertation shows that modeling the image manifold helps to achieve recognition invariance and perform robust regression within the manifold. It leverages the power of Homeomorphic Manifold Analysis (HMA) framework to utilize the known topological information about data manifolds. HMA builds mappings from a conceptual space to the feature space. These mappings are based on topological homeomorphism between points in the two spaces.
520 $a The dissertation extends this framework, applied to several applications such as human motion analysis and object recognition in conjunction with pose estimation. We propose Manifold-KPLS (MKPLS), a discriminative nonlinear model for recognition of motion sequences, applied to visual speech recognition. To tackle recognition and pose estimation from single test image, we propose a bi-nonlinear generative framework. The dissertation uses iterative inference techniques to find the optimal category and viewpoint that match a given test image. To speed up the inference, the dissertation proposes a feedforward model, which is more efficient and more accurate for solving the same problem. On the other hand, the dissertation leverages the manifold analysis to propose quantitative measurements for building a CNN variant for simultaneously solving object recognition and pose estimation.
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 Applied mathematics. $3 1069907
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0364
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Rutgers The State University of New Jersey - New Brunswick. $b Computer Science. $3 1180806
773 0 $t Dissertation Abstracts International $g 78-07B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10478534 $z click for full text (PQDT)