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. Compression and reconstruction transform pairs evolved against a representative training image reduce mean squared error (MSE) by more than 22% (1.126 dB) when subsequently applied to test images at a single level of decomposition, while evolved three-level multiresolution analysis (MRA) transforms average more than 11% (0.50 dB) MSE reduction when applied to test images in comparison to the Daubechies-4 (D4) wavelet, without increasing the size of the compressed file.
Evolved Multiresolution Analysis Transforms for Improved Image Compression and Reconstiruction under Quantization
01.04.2007
6823386 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multiresolution, dynamic, and adaptive image quantization methodology: automation and analysis
British Library Online Contents | 2003
|British Library Conference Proceedings | 1994
|Image compression using non-stationary and inhomogeneous multiresolution analysis
British Library Online Contents | 1996
|Efficient Image Coding Using Multiresolution Wavelet Transform and Vector Quantization
British Library Conference Proceedings | 1996
|Computing Shape Description Transforms on a Multiresolution Architecture
British Library Online Contents | 1992
|