Related Experiment Video
Updated: Jul 9, 2026
10:27
A Standardized Protocol for Functional Motor Mapping Using Navigated Transcranial Magnetic Stimulation
Published on: February 27, 2026
Self organizing motor maps for color-mapped image re-indexing
Sebastiano Battiato1, Francesco Rundo, Filippo Stanco
1Dipartimento di Matematica e Informatica, University of Catania, 95125 Catania, Italy. battiato@dmi.unict.it
Summary
This study introduces a new neural network algorithm for optimizing color palette re-ordering in image compression. The method achieves better compression ratios and smoother index distribution, outperforming existing techniques.
Area of Science:
- Computer Vision
- Image Processing
- Machine Learning
Background:
- Palette re-ordering enhances color-indexed image compression by improving spatial index distribution.
- Achieving optimal palette re-ordering is computationally challenging.
Purpose of the Study:
- To present a novel algorithm for the palette re-ordering problem using a motor map neural network.
- To evaluate the effectiveness of the proposed method in image compression.
Main Methods:
- Development of a novel algorithm based on motor map neural networks for palette re-ordering.
- Experimental evaluation of the algorithm's performance on image compression tasks.
Main Results:
- The proposed method demonstrates significant effectiveness in improving compression ratios.
- The algorithm achieves a reduction in zero-order entropy of local differences, indicating smoother index distribution.
- Computational complexity is competitive with existing approaches.
Conclusions:
- The motor map neural network approach offers an effective solution for the palette re-ordering problem.
- This method provides a practical advancement for color-indexed image compression.
