Invariant template matching in systems with spatiotemporal coding: a vote for instability

TL;DR

This paper introduces a neural-inspired framework based on weakly attracting sets for invariant template matching in images subject to various perturbations, aligning with biological observations and applicable to practical pattern recognition tasks.

Contribution

It proposes a unifying mathematical approach for invariant pattern recognition that is biologically plausible and effective against multiple image perturbations.

Findings

Properties of the proposed system match empirical facts in visual cognition.

The framework effectively handles image perturbations like blur, luminance, translation, and rotation.

Application examples include mental rotation, visual search, and adaptation to image changes.

Abstract

We consider the design of a pattern recognition that matches templates to images, both of which are spatially sampled and encoded as temporal sequences. The image is subject to a combination of various perturbations. These include ones that can be modeled as parameterized uncertainties such as image blur, luminance, translation, and rotation as well as unmodeled ones. Biological and neural systems require that these perturbations be processed through a minimal number of channels by simple adaptation mechanisms. We found that the most suitable mathematical framework to meet this requirement is that of weakly attracting sets. This framework provides us with a normative and unifying solution to the pattern recognition problem. We analyze the consequences of its explicit implementation in neural systems. Several properties inherent to the systems designed in accordance with our normative mathematical argument coincide with known empirical facts. This is illustrated in mental rotation, visual search and blur/intensity adaptation. We demonstrate how our results can be applied to a range of practical problems in template matching and pattern recognition.