Recover Password  New User
Undergraduate Research Project Management System

Evolved Multiresolution Analysis Transforms for Improved Ima

Status Complete
Seeking Researchers No
Start Date 09/01/2006
End Date 06/30/2007
Funding Source N/A
Funding Amount
Community Partner
Related Course
Last Updated 07/05/2008 01:25AM
Keywords

People

Faculty
  Frank Moore

Student Researchers
  Brendan Babb

Abstract

The research described in this paper uses a genetic algorithm (GA) to evolve wavelet and scaling coefficients for transforms that outperform discrete wavelet transforms (DWTs) under conditions subject to quantization. Evolved compression and reconstruction transform pairs reduce mean squared error (MSE) by more than 22% (1.126 dB) at a single level of decomposition, while evolved three-level multiresolution analysis (MRA) transforms average more than 11% (0.50 dB) MSE reduction in comparison to the Daubechies-4 (D4) wavelet, without increasing the size of the compressed file.

Shared Project Files (e.g. papers, presentations)

File name Description Uploaded by
ga_honolulu.pptPowerpoint presentation - Evolved Multiresolution Analysis Transforms for Improved Image filesvsbjb5
SSCI 2007 Paper.pdfEvolved Multiresolution Analysis Transforms for Improved Image Compression and Reconstruction under Quantizationvsbjb5