Visual learning of patterns and objects

We discuss automatic rule generation techniques for learning relational properties of 2D visual patterns and 3D objects from training samples where the observed feature values are continuous. In particular, we explore a conditional rule generation method that defines patterns (or objects) in terms o...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society. - 1996. - 27(1997), 6 vom: 15., Seite 907-17
1. Verfasser: Bischof, W F (VerfasserIn)
Weitere Verfasser: Caelli, T
Format: Aufsatz
Sprache:English
Veröffentlicht: 1997
Zugriff auf das übergeordnete Werk:IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM177505664
003 DE-627
005 20250209050812.0
007 tu
008 231223s1997 xx ||||| 00| ||eng c
028 5 2 |a pubmed25n0592.xml 
035 |a (DE-627)NLM177505664 
035 |a (NLM)18263100 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Bischof, W F  |e verfasserin  |4 aut 
245 1 0 |a Visual learning of patterns and objects 
264 1 |c 1997 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 02.10.2012 
500 |a Date Revised 11.02.2008 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We discuss automatic rule generation techniques for learning relational properties of 2D visual patterns and 3D objects from training samples where the observed feature values are continuous. In particular, we explore a conditional rule generation method that defines patterns (or objects) in terms of ordered lists of bounds on unary (pattern part) and binary (part relation) features. The technique, termed conditional rule generation, was developed to integrate relational structure representations of patterns and the generalization characteristics of evidenced-based systems. We show how this technique can be used for recognition of complex patterns and of objects in scenes. Further, we show the extent to which the learned rules can identify patterns and objects that have undergone nonrigid distortions 
650 4 |a Journal Article 
700 1 |a Caelli, T  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society  |d 1996  |g 27(1997), 6 vom: 15., Seite 907-17  |w (DE-627)NLM098252887  |x 1941-0492  |7 nnns 
773 1 8 |g volume:27  |g year:1997  |g number:6  |g day:15  |g pages:907-17 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 27  |j 1997  |e 6  |b 15  |h 907-17