Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Scene Decomposition Using the Synergetic Computer
KTH, School of Computer Science and Communication (CSC). KTH, School of Engineering Sciences (SCI).
KTH, School of Computer Science and Communication (CSC). KTH, School of Engineering Sciences (SCI).
2015 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [sv]

Den algoritm som kallas “synergetic computer” används till bildigenkänningsproblemetatt hitta och identifiera tidigare lärda objekt i en bildscen. Genom att förflytta och skala scenen finner man överlapp mellan objekten i scenen och tidigare lärda prototypmönster. Objekten hittas genom att minimera en potential som en funktion av transformationen av scenen. Genom en updateringsregel för uppmärksammhetsparametrar förhindras samma instans av ett prototypemönster från att hittas flera gånger. Den fullständiga strateg in klarar av att dela uppscener i prototypmönstren i ideala fall. Det utgör en kvalitativ förbättring jämfört med scenuppdelningen i prototypmönster beskriven av H.Haken i den ursprungliga boken om ”synergetic computer” i det att flera identiska objekt kan hittas i en scen.

Abstract [en]

The synergetic computer is applied to the image recognition problem of finding and identifying previously learned objects in a scene. Translation and scaling is applied to the scene to align the objects with known prototype patterns. The objects are located by minimizing a potential as a function of the applied transform. An update rule for attention parameters prohibits the same object instance from being found multiple times. The complete strategy is successful in decomposing scenes in idealized cases. It presents a qualitative improvement over the scene decomposition procedure described by H. Haken in the original book on the synergetic computer in that several identical object can be found within a scene.

Place, publisher, year, edition, pages
2015. , 43 p.
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-167035OAI: oai:DiVA.org:kth-167035DiVA: diva2:812988
Supervisors
Available from: 2015-05-21 Created: 2015-05-21 Last updated: 2015-05-25Bibliographically approved

Open Access in DiVA

No full text

By organisation
School of Computer Science and Communication (CSC)School of Engineering Sciences (SCI)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 92 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf