The quantization error in a Self-Organizing Map as a contrast and colour specific indicator of single-pixel change in large random patterns

TL;DR

This paper demonstrates that the quantization error in Self-Organizing Maps can reliably detect minute contrast and color changes at the pixel level in large images, surpassing human visual detection and traditional metrics.

Contribution

The study reveals that SOM quantization error can discriminate fine contrast and color differences, offering a new tool for high-resolution image change detection beyond existing methods.

Findings

SOM QE detects single-pixel contrast changes in images with up to five million pixels.

QE surpasses RGB Mean in sensitivity for contrast change detection.

QE is sensitive to contrast and color changes but not to spatial rearrangements of contrast elements.

Abstract

The quantization error in a fixed-size Self-Organizing Map (SOM) with unsupervised winner-take-all learning has previously been used successfully to detect, in minimal computation time, highly meaningful changes across images in medical time series and in time series of satellite images. Here, the functional properties of the quantization error in SOM are explored further to show that the metric is capable of reliably discriminating between the finest differences in local contrast intensities and contrast signs. While this capability of the QE is akin to functional characteristics of a specific class of retinal ganglion cells (the so-called Y-cells) in the visual systems of the primate and the cat, the sensitivity of the QE surpasses the capacity limits of human visual detection. Here, the quantization error in the SOM is found to reliably signal changes in contrast or colour when contrast information is removed from or added to the image, but not when the amount and relative weight of contrast information is constant and only the local spatial position of contrast elements in the pattern changes. While the RGB Mean reflects coarser changes in colour or contrast well enough, the SOM-QE is shown to outperform the RGB Mean in the detection of single-pixel changes in images with up to five million pixels. This could have important implications in the context of unsupervised image learning and computational building block approaches to large sets of image data (big data), including deep learning blocks, and automatic detection of contrast change at the nanoscale in Transmission or Scanning Electron Micrographs (TEM, SEM), or at the subpixel level in multispectral and hyper-spectral imaging data.