Fractal Coding by Means of Local Feature Histograms
Per-Erik Forssén, Björn JohanssonLiTH-ISY-R-2295
September 2000
Abstract
This report describes an experimental still image coder that grew out of a project in the graduate course ``Advanced Video Coding'' in spring 2000.The project has investigated the idea to use local orientation histograms in fractal coding. Instead of performing a correlation-like grey-level matching of image regions, the block search is made by matching feature histograms of the block contents. The feature investigated in this report is local orientation, but in principle other features could be used as well.
In its current state the coder does not outperform state of the art still image coders, but the block-search strategy seems promising, and will probably prove useful in several other applications.
Full Paper
Portable document format file PDF (
Bibtex entry
@TechReport{fj2000, author = {Per-Erik Forss\'en and Bj{\"o}rn Johansson}, title = {Fractal Coding by Means of Local Feature Histograms}, institution = {Dept. EE, Link\"oping University}, year = {2000}, type = {Report}, number = {LiTH-ISY-R-2295}, address = {SE-581 83 Link\"oping, Sweden}, month = {September}, }
Per-Erik Forssén
Contact:
Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654
< >
My pages:
Informationsansvarig: Per-Erik Forssén
Senast uppdaterad: 2024-09-28