Image enhancement by morphological pyramid decomposition and modified reconstruction

An algorithm for multiresolution pyramid decomposition is described. At each stage, the smoothed ("lowpass") image is obtained by combining morphological grayscale opening and closing. Using this technique, we avoid the systematic bias of traditional approaches, as illustrated by an exampl...

Full description

Saved in:
Bibliographic Details
Main Authors: Floreby, L., Sattar, F., Salomonsson, G.
Format: Conference Proceeding
Language:English
Subjects:
Applied sciences
Detectors
Exact sciences and technology
Filtering theory
Filters
Image edge detection
Image enhancement
Image processing
Image reconstruction
Image resolution
Information, signal and communications theory
Signal processing
Signal processing algorithms
Signal resolution
Telecommunications and information theory
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An algorithm for multiresolution pyramid decomposition is described. At each stage, the smoothed ("lowpass") image is obtained by combining morphological grayscale opening and closing. Using this technique, we avoid the systematic bias of traditional approaches, as illustrated by an example. As our application, we perform image enhancement by modifying the reconstruction scheme using a morphological edge detector. The processing scheme offers a method for edge-preserving noise (speckle) suppression, in which only a minor number of multiplications is required.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1997.595317