Imaging system for detection, classification and quantification

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/203599
Download file(s):
File Description SizeFormat 
203599.pdfFulltext6.45 MBAdobe PDFThumbnail
View/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPfreundschuh, Simon
dc.contributor.departmentChalmers tekniska högskola / Institutionen för matematiska vetenskapersv
dc.contributor.departmentChalmers University of Technology / Department of Mathematical Sciencesen
dc.date.accessioned2019-07-03T13:31:30Z-
dc.date.available2019-07-03T13:31:30Z-
dc.date.issued2014
dc.identifier.urihttps://hdl.handle.net/20.500.12380/203599-
dc.description.abstractThis thesis was conducted at the Fraunhofer Chalmers Centre for Industrial Mathematics in collaboration with the Fraunhofer-Institut f¨ur Techno- und Wirtschaftsmathematik. The aim of this thesis is to develop an imaging system for the automated detection of holes in images of supermarket shelves. The proposed approach uses an unsupervised segmentation method to presegment the image into homogeneous regions. Each of those image regions is then classified separately using a support vector machine. Finally, suitable bounding boxes are found for image regions that are likely to represent holes. Apart from the SVM classifier also an AdaBoost classifier and a structural classifier based on conditional random fields are implemented and tested. This thesis describes the implementation and performance characteristics of the resulting imaging system, which is implemented using the ToolIP graphical image processing framework and C++.
dc.language.isoeng
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectGrundläggande vetenskaper
dc.subjectMatematik
dc.subjectBasic Sciences
dc.subjectMathematics
dc.titleImaging system for detection, classification and quantification
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster Thesisen
dc.type.uppsokH
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.