På den här sidan
'/%3e%3c/svg%3e)
Bibliografi, Ej skönlitteratur, Text · Engelska
Probabilistic and biologically inspired feature representations
Michael Felsberg (Författare)
Specialiserad
ISBN 9781681730240 · (electronic bk.), ISBN 1681730243 · (electronic bk.), DOI 10.2200/S00851ED1V01Y201804COV016
utgivning
[San Rafael, California] : Morgan & Claypool Publishers, 2018, [2018]1 online resource (xiii, 89 pages)
Seriemedlemskap
Synthesis lectures on computer vision · ISSN 2153-1064, ISSN 2153-1056 · Synthesis lectures on computer vision ; #16#16.Michael Felsberg
E-bok
Tillgänglighet utifrån medietyp
ämne
Computer vision., Pattern recognition systems., COMPUTERS / General, channel representation, channel-coded feature map, feature descriptor, signature, histogram, BildbehandlingAnnat bärarformat
ISBN 9781681730233, ISBN 9781681733661 · ISBN 9781681730233, ISBN 9781681733661 (Print version:)Sammanfattning
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.
Innehållsförteckning
1. Introduction -- 1.1 Feature design -- 1.2 Channel representations: a design choice --, 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 --, 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 --, 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 --, 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 --, 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 --, 7. Conclusions -- Bibliography -- Author's biography -- Index.
Detaljer
Medverkan och funktion
Michael Felsberg (Författare)klassifikation
006.37 (DDK-klassifikation)målgrupp
SpecialiseradIdentifikator
ISBN 9781681730240 · (electronic bk.), ISBN 1681730243 · (electronic bk.), DOI 10.2200/S00851ED1V01Y201804COV016Indirekt identifierad av
ISBN 9781681730233, ISBN 9781681733661har titel
Probabilistic and biologically inspired feature representationsupphovsuppgift
Michael Felsbergutgivning
[San Rafael, California] : Morgan & Claypool Publishers, 2018, [2018]copyright
©2018omfång
1 online resource (xiii, 89 pages)anmärkning
- Includes bibliographical references (pages 71-81) and index.
Mått
nÖvriga fysiska detaljer
illustrations.Illustrativt innehåll
Illustrationer finns men typen specificeras ejAnnat bärarformat
ISBN 9781681730233, ISBN 9781681733661 · ISBN 9781681730233, ISBN 9781681733661 (Print version:)Seriemedlemskap
Synthesis lectures on computer vision · ISSN 2153-1064, ISSN 2153-1056 · Synthesis lectures on computer vision ; #16#16.färginnehåll
Flera färgerkontrollnummer
8jnv7rn26zlq2xqzResursens ID / Permalänk: https://libris.kb.se/8jnv7rn26zlq2xqz#it
Ladda ner metadata: JSON-LD · Turtle · RDF/XML · MARC21 (ISO 2709) · MARC21 (XML)