Show simple item record

AuthorFay, Rebeccadc.contributor.author
Date of accession2016-03-14T15:19:09Zdc.date.accessioned
Available in OPARU since2016-03-14T15:19:09Zdc.date.available
Year of creation2007dc.date.created
AbstractThis work offers a novel approach for solving muti-class object recognition problems by dividing the complex task into several hierarchically structured sub-problems that are easier to solve. The work at hand covers several aspects of object recognition with hierarchical neural networks: 1. Generation of appropriate classifier hierarchies; 2. Evaluation of hierarchies (information fusion); 3. Selection of suitable features for the classification; 4. Extensibility/adaptivity of the hierarchies; 5. Generation of similarity preserving sparse binary codes. The selection of suitable feature types for the classification of objects from various domains is an important aspect for the recognition of three-dimensional objects. In the context of this work diverse feature types were deployed and evaluated. Different strategies for the retrieval of the combined classification result from the classifier hierarchies were developed and evaluated. The most promising approaches were the retrieval strategy similar to decision trees, the retrieval strategy utilizing the Dempster-Shafer evidence theory as well as the retrieval strategy utilizing similarity preserving codes and inter-state decision templates. The generation of similarity preserving sparse binary codes is an additional aspect of the object recognition with hierarchical neural network classifiers. Within the scope of this work several strategies for the generation of such codes based on the activation of the neural classifiers within the hierarchy were developed and evaluated. Another focus was the incremental learning of hitherto unknown objects. In complex real-world environments this is an often desirable capability as the confrontation with so far unfamiliar objects is very likely. Within the scope of this work a method for subsequently learning new objects in an efficient manner without negatively influencing the classification performance of previously learnt objects.dc.description.abstract
Languageendc.language.iso
PublisherUniversität Ulmdc.publisher
LicenseStandard (Fassung vom 03.05.2003)dc.rights
Link to license texthttps://oparu.uni-ulm.de/xmlui/license_v1dc.rights.uri
KeywordFeature selectiondc.subject
KeywordHierarchical neural networksdc.subject
KeywordIncremental learningdc.subject
KeywordInformation fusiondc.subject
KeywordObject recognitiondc.subject
Dewey Decimal GroupDDC 004 / Data processing & computer sciencedc.subject.ddc
LCSHDempster-Shafer theorydc.subject.lcsh
LCSHUncertaintydc.subject.lcsh
MeSHNeoplasms; Classificationdc.subject.mesh
TitleFeature selection and information fusion in hierarchical neural networks for iterative 3D-object recognitiondc.title
Resource typeDissertationdc.type
DOIhttp://dx.doi.org/10.18725/OPARU-893dc.identifier.doi
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-vts-60447dc.identifier.urn
GNDDatenfusiondc.subject.gnd
FacultyFakultät für Ingenieurwissenschaften und Informatikuulm.affiliationGeneral
Date of activation2007-10-30T11:41:39Zuulm.freischaltungVTS
Peer reviewneinuulm.peerReview
Shelfmark print versionZ: J-H 11.601 ; W: W-H 9.805uulm.shelfmark
DCMI TypeTextuulm.typeDCMI
VTS ID6044uulm.vtsID
CategoryPublikationenuulm.category
Bibliographyuulmuulm.bibliographie


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record