Kasa

The RGFF Representational Model: A Scheme That Learns Functions For Extracting "Visible Patterns" (1998)

Cached


Download Links

[decsai.ugr.es]

Save to List
Add to CollectionCorrect Errors
Monitor Changes
by Rosa Rodriguez-Sanchez , J. A. Garcia , J. Fdez-Valdivia , Xose R. Fdez-Vidal
Venue: IEEE TRANS. PATTERN ANAL. MACH. INTELL
Citations: 2 - 2 self
SummaryActiveBibliographyCo-citationClustered DocumentsVersion History
BibTeX
@ARTICLE{Rodriguez-Sanchez98thergff,
author = {Rosa Rodriguez-Sanchez and J. A. Garcia and J. Fdez-Valdivia and Xose R. Fdez-Vidal},title = {The RGFF Representational Model: A Scheme That Learns Functions For Extracting "Visible Patterns"},
journal = {IEEE TRANS. PATTERN ANAL. MACH. INTELL},
year = {1998},volume = {21}
}
Bookmark

CiteSeerX
10.1.1.48.857

Join the conversation
Abstract
This paper describes a system for the automatically learned partitioning of "visual patterns" in 2D images,based on a sophisticated, band-pass, filtering operation, with fixed scale and orientation sensitivity. The process of image formation which leads to an image requiring separation is the superposition orsimple addition of objects. In this scheme, the "visible patterns" are defined as the features which have the highest degree of alignment in the statistical structure across different frequency bands.The analysis reorganizes the image according to a constraint of invariance in the statistical structure and consists of three stages: (i) pre-attentive stage; (ii) integration stage; and (iii)learning stage. The first stage takes the input image and performs filtering with a set of log-Gabor filters. Based on their responses, activated filters which are selectively sensitive to patterns in theimage are short listed. In the integration stage, common grounds between several activate...
Citations
2317 A computational approach to edge detection - Canny
987 A note on two problems in...