skip to content
Probabilistic and biologically inspired feature representations Preview this item
ClosePreview this item
Checking...

Probabilistic and biologically inspired feature representations

Author: Michael Felsberg
Publisher: [San Rafael, California] : Morgan & Claypool Publishers, [2018] ©2018
Series: Synthesis lectures on computer vision, #16.
Edition/Format:   eBook : Document : EnglishView all editions and formats
Summary:
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  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

Find a copy online

Links to this item

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Genre/Form: Electronic books
Additional Physical Format: Print version:
Material Type: Document, Internet resource
Document Type: Internet Resource, Computer File
All Authors / Contributors: Michael Felsberg
ISBN: 9781681730240 1681730243
OCLC Number: 1038017379
Description: 1 online resource (xiii, 89 pages) : illustrations.
Contents: 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.
Series Title: Synthesis lectures on computer vision, #16.
Responsibility: Michael Felsberg.
More information:

Abstract:

Presents 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  Read more...

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


Primary Entity

<http://www.worldcat.org/oclc/1038017379> # Probabilistic and biologically inspired feature representations
    a schema:MediaObject, schema:Book, schema:CreativeWork ;
    library:oclcnum "1038017379" ;
    library:placeOfPublication <http://id.loc.gov/vocabulary/countries/cau> ;
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Topic/computer_vision> ; # Computer vision
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Topic/pattern_recognition_systems> ; # Pattern recognition systems
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Thing/signature> ; # signature
    schema:about <http://dewey.info/class/006.37/e23/> ;
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Thing/channel_representation> ; # channel representation
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Thing/histogram> ; # histogram
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Thing/feature_descriptor> ; # feature descriptor
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Thing/channel_coded_feature_map> ; # channel-coded feature map
    schema:about <http://experiment.worldcat.org/entity/work/data/5217221306#Topic/computers_general> ; # COMPUTERS / General
    schema:author <http://experiment.worldcat.org/entity/work/data/5217221306#Person/felsberg_michael> ; # Michael Felsberg
    schema:bookFormat schema:EBook ;
    schema:copyrightYear "2018" ;
    schema:datePublished "2018" ;
    schema:description "1. Introduction -- 1.1 Feature design -- 1.2 Channel representations: a design choice --"@en ;
    schema:description "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."@en ;
    schema:exampleOfWork <http://worldcat.org/entity/work/id/5217221306> ;
    schema:genre "Electronic books"@en ;
    schema:inLanguage "en" ;
    schema:isPartOf <http://worldcat.org/issn/2153-1064> ; # Synthesis lectures on computer vision,
    schema:isPartOf <http://worldcat.org/issn/2153-1056> ; # Synthesis lectures on computer vision ;
    schema:isSimilarTo <http://worldcat.org/entity/work/data/5217221306#CreativeWork/> ;
    schema:name "Probabilistic and biologically inspired feature representations"@en ;
    schema:productID "1038017379" ;
    schema:url <http://public.eblib.com/choice/PublicFullRecord.aspx?p=5406481> ;
    schema:url <http://search.ebscohost.com/login.aspx?direct=true&scope=site&db=nlebk&db=nlabk&AN=1822199> ;
    schema:url <http://dx.doi.org/10.2200/S00851ED1V01Y201804COV016> ;
    schema:url <http://proxy.library.carleton.ca/login?url=http://dx.doi.org/10.2200/S00851ED1V01Y201804COV016> ;
    schema:url <http://liverpool.idm.oclc.org/login?url=http://dx.doi.org/10.2200/S00851ED1V01Y201804COV016> ;
    schema:url <https://doi.org/10.2200/S00851ED1V01Y201804COV016> ;
    schema:workExample <http://worldcat.org/isbn/9781681730240> ;
    schema:workExample <http://dx.doi.org/10.2200/S00851ED1V01Y201804COV016> ;
    wdrs:describedby <http://www.worldcat.org/title/-/oclc/1038017379> ;
    .


Related Entities

<http://experiment.worldcat.org/entity/work/data/5217221306#Person/felsberg_michael> # Michael Felsberg
    a schema:Person ;
    schema:familyName "Felsberg" ;
    schema:givenName "Michael" ;
    schema:name "Michael Felsberg" ;
    .

<http://experiment.worldcat.org/entity/work/data/5217221306#Thing/channel_coded_feature_map> # channel-coded feature map
    a schema:Thing ;
    schema:name "channel-coded feature map" ;
    .

<http://experiment.worldcat.org/entity/work/data/5217221306#Thing/channel_representation> # channel representation
    a schema:Thing ;
    schema:name "channel representation" ;
    .

<http://experiment.worldcat.org/entity/work/data/5217221306#Thing/feature_descriptor> # feature descriptor
    a schema:Thing ;
    schema:name "feature descriptor" ;
    .

<http://experiment.worldcat.org/entity/work/data/5217221306#Topic/computers_general> # COMPUTERS / General
    a schema:Intangible ;
    schema:name "COMPUTERS / General"@en ;
    .

<http://experiment.worldcat.org/entity/work/data/5217221306#Topic/pattern_recognition_systems> # Pattern recognition systems
    a schema:Intangible ;
    schema:name "Pattern recognition systems"@en ;
    .

<http://proxy.library.carleton.ca/login?url=http://dx.doi.org/10.2200/S00851ED1V01Y201804COV016>
    rdfs:comment "Synthesis digital library of engineering and computer science" ;
    .

<http://worldcat.org/entity/work/data/5217221306#CreativeWork/>
    a schema:CreativeWork ;
    schema:description "Print version:" ;
    schema:isSimilarTo <http://www.worldcat.org/oclc/1038017379> ; # Probabilistic and biologically inspired feature representations
    .

<http://worldcat.org/isbn/9781681730240>
    a schema:ProductModel ;
    schema:isbn "1681730243" ;
    schema:isbn "9781681730240" ;
    .

<http://worldcat.org/issn/2153-1056> # Synthesis lectures on computer vision ;
    a bgn:PublicationSeries ;
    schema:hasPart <http://www.worldcat.org/oclc/1038017379> ; # Probabilistic and biologically inspired feature representations
    schema:issn "2153-1056" ;
    schema:name "Synthesis lectures on computer vision ;" ;
    .

<http://worldcat.org/issn/2153-1064> # Synthesis lectures on computer vision,
    a bgn:PublicationSeries ;
    schema:hasPart <http://www.worldcat.org/oclc/1038017379> ; # Probabilistic and biologically inspired feature representations
    schema:issn "2153-1064" ;
    schema:name "Synthesis lectures on computer vision," ;
    .


Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.