Core Issues in Graph Based Perceptual Organization: Spectral Cut Measures, Learning
Grouping is a vital precursor to object recognition. The complexity of the object recognition process can be reduced to a large extent by using a frontend grouping process. In this dissertation, a grouping framework based on spectral methods for graphs is used. The objects are segmented from the bac...
| Main Author: | |
|---|---|
| Format: | Others |
| Published: |
Scholar Commons
2004
|
| Subjects: | |
| Online Access: | https://scholarcommons.usf.edu/etd/1255 https://scholarcommons.usf.edu/cgi/viewcontent.cgi?article=2254&context=etd |