大葉大學圖書館 |

Probabilistic and biologically inspired feature representations /

紀錄類型:	書目-電子資源 : Monograph/item
杜威分類號:	006.37
書名/作者:	Probabilistic and biologically inspired feature representations // Michael Felsberg.
作者:	Felsberg, Michael,
出版者:	[San Rafael, California] : : Morgan & Claypool,, 2018.
面頁冊數:	1 PDF (xiii, 89 pages) : : illustrations.
附註:	Part of: Synthesis digital library of engineering and computer science.
標題:	Computer vision.
標題:	Pattern recognition systems.
ISBN:	9781681730240
書目註:	Includes bibliographical references (pages 71-81) and index.
內容註:	1. Introduction -- 1.1 Feature design -- 1.2 Channel representations: a design choice --
摘要、提要註:	This text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes. In their unique combination of properties, channel representations become a visual Swiss army knife--they can be used for image enhancement, visual object tracking, as 2D and 3D descriptors, and for pose estimation. In the chapters of this text, the framework of channel representations will be introduced and its attributes will be elaborated, as well as further insight into its probabilistic modeling and algorithmic implementation will be given. Channel representations are a useful toolbox to represent visual information for machine learning, as they establish a generic way to compute popular descriptors such as HOG, SIFT, and SHOT. Even in an age of deep learning, they provide a good compromise between hand-designed descriptors and a-priori structureless feature spaces as seen in the layers of deep networks.
電子資源:	https://ieeexplore.ieee.org/servlet/opac?bknumber=8369413

Probabilistic and biologically inspired feature representations /
Felsberg, Michael,

Probabilistic and biologically inspired feature representations /Michael Felsberg. - [San Rafael, California] :Morgan & Claypool,2018. - 1 PDF (xiii, 89 pages) :illustrations. - Synthesis lectures on computer vision,# 162153-1064 ;. - Synthesis digital library of engineering and computer science..

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 71-81) and index.

1. Introduction -- 1.1 Feature design -- 1.2 Channel representations: a design choice --

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

This text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes. In their unique combination of properties, channel representations become a visual Swiss army knife--they can be used for image enhancement, visual object tracking, as 2D and 3D descriptors, and for pose estimation. In the chapters of this text, the framework of channel representations will be introduced and its attributes will be elaborated, as well as further insight into its probabilistic modeling and algorithmic implementation will be given. Channel representations are a useful toolbox to represent visual information for machine learning, as they establish a generic way to compute popular descriptors such as HOG, SIFT, and SHOT. Even in an age of deep learning, they provide a good compromise between hand-designed descriptors and a-priori structureless feature spaces as seen in the layers of deep networks.

Mode of access: World Wide Web.

ISBN: 9781681730240

Standard No.: 10.2200/S00851ED1V01Y201804COV016doiSubjects--Topical Terms:

403529
Computer vision.
Subjects--Index Terms:

channel representationIndex Terms--Genre/Form:

336502
Electronic books.

LC Class. No.: TA1634 / .F456 2018

Dewey Class. No.: 006.37

Probabilistic and biologically inspired feature representations /
LDR:04510nmm 2200601 i 4500 001 509528
003 IEEE
005 20180601104903.0
006 m eo d
007 cr cn |||m|||a
008 210524s2018 caua foab 001 0 eng d
020 $a 9781681730240 $q ebook
020 $z 9781681730233 $q paperback
020 $z 9781681733661 $q hardcover
024 7 $a 10.2200/S00851ED1V01Y201804COV016 $2 doi
035 $a (CaBNVSL)swl408348
035 $a (OCoLC)1038017379
035 $a 8369413
040 $a CaBNVSL $b eng $e rda $c CaBNVSL $d CaBNVSL
050 4 $a TA1634 $b .F456 2018
082 0 4 $a 006.37 $2 23
100 1 $a Felsberg, Michael, $e author. $3 729073
245 1 0 $a Probabilistic and biologically inspired feature representations / $c Michael Felsberg.
260 1 $a [San Rafael, California] : $b Morgan & Claypool, $c 2018.
264 1 $a [San Rafael, California] : $b Morgan & Claypool, $c 2018.
300 $a 1 PDF (xiii, 89 pages) : $b illustrations.
336 $a text $2 rdacontent
337 $a electronic $2 isbdmedia
338 $a online resource $2 rdacarrier
490 1 $a Synthesis lectures on computer vision, $x 2153-1064 ; $v # 16
500 $a Part of: Synthesis digital library of engineering and computer science.
504 $a Includes bibliographical references (pages 71-81) and index.
505 0 $a 1. Introduction -- 1.1 Feature design -- 1.2 Channel representations: a design choice --
505 8 $a 2. Basics of feature design -- 2.1 Statistical properties -- 2.2 Invariance and equivariance -- 2.3 Sparse representations, histograms, and signatures -- 2.4 Grid-based feature representations -- 2.5 Links to biologically inspired models --
505 8 $a 3. Channel coding of features -- 3.1 Channel coding -- 3.2 Enhanced distribution field tracking -- 3.3 Orientation scores as channel representations -- 3.4 Multi-dimensional coding --
505 8 $a 4. Channel-coded feature maps -- 4.1 Definition of channel-coded feature maps -- 4.2 The HOG descriptor as a CCFM -- 4.3 The SIFT descriptor as a CCFM -- 4.4 The SHOT descriptor as a CCFM --
505 8 $a 5. CCFM decoding and visualization -- 5.1 Channel decoding -- 5.2 Decoding based on frame theory -- 5.3 Maximum entropy decoding -- 5.4 Relation to other de-featuring methods --
505 8 $a 6. Probabilistic interpretation of channel representations -- 6.1 On the distribution of channel values -- 6.2 Comparing channel representations -- 6.3 Comparing using divergences -- 6.4 Uniformization and copula estimation --
505 8 $a 7. Conclusions -- Bibliography -- Author's biography -- Index.
506 $a Abstract freely available; full-text restricted to subscribers or individual document purchasers.
510 0 $a Compendex
510 0 $a INSPEC
510 0 $a Google scholar
510 0 $a Google book search
520 3 $a This text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes. In their unique combination of properties, channel representations become a visual Swiss army knife--they can be used for image enhancement, visual object tracking, as 2D and 3D descriptors, and for pose estimation. In the chapters of this text, the framework of channel representations will be introduced and its attributes will be elaborated, as well as further insight into its probabilistic modeling and algorithmic implementation will be given. Channel representations are a useful toolbox to represent visual information for machine learning, as they establish a generic way to compute popular descriptors such as HOG, SIFT, and SHOT. Even in an age of deep learning, they provide a good compromise between hand-designed descriptors and a-priori structureless feature spaces as seen in the layers of deep networks.
530 $a Also available in print.
538 $a Mode of access: World Wide Web.
588 $a Title from PDF title page (viewed on May 29, 2018).
650 0 $a Computer vision. $3 403529
650 0 $a Pattern recognition systems. $3 189561
653 $a channel representation
653 $a channel-coded feature map
653 $a feature descriptor
653 $a signature
653 $a histogram
655 0 $a Electronic books. $2 local $3 336502
776 0 8 $i Print version: $z 9781681730233 $z 9781681733661
830 0 $a Synthesis digital library of engineering and computer science. $3 461208
830 0 $a Synthesis lectures on computer vision ; $v #9. $x 2153-1056 $3 713984
856 4 2 $3 Abstract with links to resource $u https://ieeexplore.ieee.org/servlet/opac?bknumber=8369413