Using the quantization error from Self-Organized Map (SOM) output for detecting critical variability in large bodies of image time series in less than a minute

TL;DR

This paper demonstrates that the quantization error from Self-Organized Map (SOM) effectively detects critical variability in large image time series, providing a fast and reliable indicator of changes in image homogeneity.

Contribution

It introduces the use of SOM quantization error as a quick, reliable metric for detecting critical changes in large image time series, especially in medical and satellite images.

Findings

QE increases linearly with variability in contrast content

SOM quantization error reliably indicates critical changes

Detection can be performed in less than a minute

Abstract

The quantization error (QE) from SOM applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images, is proven a reliable indicator of potentially critical changes in image homogeneity. The QE is shown to increase linearly with the variability in spatial contrast contents across time when contrast intensity is kept constant.