From global to local statistical shape priors : novel methods to obtain accurate reconstruction results with a limited amount of training shapes

This book proposes a new approach to handle the problem of limited training data. Common approaches to cope with this problem are to model the shape variability independently across predefined segments or to allow artificial shape variations that cannot be explained through the training data, both o...

Full description

Saved in:
Bibliographic Details
Main Author Last, Carsten (Author)
Format Electronic eBook
LanguageEnglish
Published Cham, Switzerland : Springer, [2017]
SeriesStudies in systems, decision and control ; v. 98.
Subjects
Online AccessFull text
ISBN9783319535081
9783319535074
Physical Description1 online resource

Cover

LEADER 00000cam a2200000Ii 4500
001 99896
003 CZ-ZlUTB
005 20251008112002.0
006 m o d
007 cr cnu|||unuuu
008 170316s2017 sz ob 000 0 eng d
040 |a N$T  |b eng  |e rda  |e pn  |c N$T  |d N$T  |d EBLCP  |d YDX  |d GW5XE  |d OCLCF  |d NJR  |d UAB  |d IOG  |d AZU  |d UPM  |d MERER  |d ESU  |d OCLCQ  |d JBG  |d IAD  |d ICW  |d ICN  |d COO  |d OTZ  |d VT2  |d OCLCQ  |d U3W  |d CAUOI  |d KSU  |d AU@  |d OCLCQ  |d WYU  |d UKMGB  |d UKAHL  |d OCLCQ  |d ERF  |d UKBTH  |d OCLCQ  |d SRU 
020 |a 9783319535081  |q (electronic bk.) 
020 |z 9783319535074 
024 7 |a 10.1007/978-3-319-53508-1  |2 doi 
035 |a (OCoLC)976146102  |z (OCoLC)978689748  |z (OCoLC)978758877  |z (OCoLC)979016382  |z (OCoLC)979401810  |z (OCoLC)979491912  |z (OCoLC)979727921  |z (OCoLC)984864544  |z (OCoLC)999453488  |z (OCoLC)1005774152  |z (OCoLC)1011795739  |z (OCoLC)1048109183  |z (OCoLC)1058433829  |z (OCoLC)1066460553  |z (OCoLC)1066476703  |z (OCoLC)1086519618  |z (OCoLC)1112558523  |z (OCoLC)1112866577  |z (OCoLC)1112924008  |z (OCoLC)1127176573 
100 1 |a Last, Carsten,  |e author. 
245 1 0 |a From global to local statistical shape priors :  |b novel methods to obtain accurate reconstruction results with a limited amount of training shapes /  |c Carsten Last. 
264 1 |a Cham, Switzerland :  |b Springer,  |c [2017] 
264 4 |c ©2017 
300 |a 1 online resource 
336 |a text  |b txt  |2 rdacontent 
337 |a počítač  |b c  |2 rdamedia 
338 |a online zdroj  |b cr  |2 rdacarrier 
490 1 |a Studies in systems, decision and control ;  |v volume 98 
504 |a Includes bibliographical references. 
505 0 |a Basics -- Statistical Shape Models (SSMs) -- A Locally Deformable Statistical Shape Model (LDSSM) -- Evaluation of the Locally Deformable Statistical Shape Model -- Global-To-Local Shape Priors for Variational Level Set Methods -- Evaluation of the Global-To-Local Variational Formulation -- Conclusion and Outlook. 
506 |a Plný text je dostupný pouze z IP adres počítačů Univerzity Tomáše Bati ve Zlíně nebo vzdáleným přístupem pro zaměstnance a studenty 
520 |a This book proposes a new approach to handle the problem of limited training data. Common approaches to cope with this problem are to model the shape variability independently across predefined segments or to allow artificial shape variations that cannot be explained through the training data, both of which have their drawbacks. The approach presented uses a local shape prior in each element of the underlying data domain and couples all local shape priors via smoothness constraints. The book provides a sound mathematical foundation in order to embed this new shape prior formulation into the well-known variational image segmentation framework. The new segmentation approach so obtained allows accurate reconstruction of even complex object classes with only a few training shapes at hand. 
590 |a SpringerLink  |b Springer Complete eBooks 
650 0 |a Image processing  |x Digital techniques. 
655 7 |a elektronické knihy  |7 fd186907  |2 czenas 
655 9 |a electronic books  |2 eczenas 
776 0 8 |i Print version:  |a Last, Carsten.  |t From global to local statistical shape priors.  |d Cham, Switzerland : Springer, [2017]  |z 3319535072  |z 9783319535074  |w (OCoLC)968663428 
830 0 |a Studies in systems, decision and control ;  |v v. 98. 
856 4 0 |u https://proxy.k.utb.cz/login?url=https://link.springer.com/10.1007/978-3-319-53508-1 
992 |c NTK-SpringerENG 
999 |c 99896  |d 99896 
993 |x NEPOSILAT  |y EIZ