Spatio-Colour Aspl\"und 's Metric and Logarithmic Image Processing for Colour Images (LIPC)

TL;DR

This paper introduces a new spatio-colour Aspl"und's metric based on the LIPC model, enhancing pattern matching in colour images by being insensitive to lighting changes and noise.

Contribution

It extends previous scalar and multivariate Aspl"und's metrics to a vectorial model for colour images using LIPC, incorporating robustness to lighting and noise.

Findings

The metric is insensitive to lighting variations.

A noise-robust variant improves pattern matching.

Effective in colour image analysis.

Abstract

Aspl\"und 's metric, which is useful for pattern matching, consists in a double-sided probing, i.e. the over-graph and the sub-graph of a function are probed jointly. This paper extends the Aspl\"und 's metric we previously defined for colour and multivariate images using a marginal approach (i.e. component by component) to the first spatio-colour Aspl\"und 's metric based on the vectorial colour LIP model (LIPC). LIPC is a non-linear model with operations between colour images which are consistent with the human visual system. The defined colour metric is insensitive to lighting variations and a variant which is robust to noise is used for colour pattern matching.