Applying Dynamic Link Matching to Object Recognition in Real World Images
| Autor: | Wolfgang Konen, Jan C. Vorbrüggen |
|---|---|
| Rok vydání: | 1993 |
| Předmět: |
Computer science
business.industry 3D single-object recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Cognitive neuroscience of visual object recognition Dynamic link matching Computer vision Boundary value problem Artificial intelligence Sparse approximation business Object (computer science) Image (mathematics) |
| Zdroj: | ICANN ’93 ISBN: 9783540198390 |
| DOI: | 10.1007/978-1-4471-2063-6_288 |
| Popis: | We apply the dynamic link matching algorithm to object recognition in gray level images. The algorithm is able to map from one view of an object to different-e. g., translated, rotated, or mirror-reflected—views, being at the same time tolerant of small distortions. A sparse representation (10%) of the image data is used as a boundary condition for a self-organizing mechanism which performs the object match within a modest number of iterations (~102). The mechanism can be derived from local neural dynamics [1]. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|