A STUDY ON IMAGE COMPRESSION WITH NEURAL NETWORKS USING MODIFIED LEVENBERG METHOD
Keywords:
Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network
Abstract
In this paper, an adaptive method for image compression that is subjective on neural networks based on complexity level of the image. The multilayer perceptron artificial neural network uses the different Back-Propagation artificial neural networks in processing of the image. The original images taken, for instance 256*256 pixels of bitmap image, each block of image into one network selection, according to each block the value of pixels in image complexity value is calculated. To estimate each value of the images in a block can be evaluated and trained. Best PSNR in selecting images to be compressed with a modification Levenberg-Marquart for MLP neural network is taken. The algorithm taken a good research of result to each block of image. The taken time reduces the learning procedure for running each block of images. Finally, a neural network taken for the Back Propagation artificial neural network.
Downloads
- Article PDF
- TEI XML Kaleidoscope (download in zip)* (Beta by AI)
- Lens* NISO JATS XML (Beta by AI)
- HTML Kaleidoscope* (Beta by AI)
- DBK XML Kaleidoscope (download in zip)* (Beta by AI)
- LaTeX pdf Kaleidoscope* (Beta by AI)
- EPUB Kaleidoscope* (Beta by AI)
- MD Kaleidoscope* (Beta by AI)
- FO Kaleidoscope* (Beta by AI)
- BIB Kaleidoscope* (Beta by AI)
- LaTeX Kaleidoscope* (Beta by AI)
How to Cite
Published
2011-01-15
Issue
Section
License
Copyright (c) 2011 Authors and Global Journals Private Limited
This work is licensed under a Creative Commons Attribution 4.0 International License.