Neuro-inspired edge feature fusion using Choquet integrals

TL;DR

This paper introduces a neuro-inspired edge feature fusion method using generalized Choquet integrals to model early visual cortex neuron behavior, resulting in a novel edge detection algorithm tested on boundary detection datasets.

Contribution

It proposes a new fusion approach for early vision primitives based on generalized Choquet integrals, inspired by neural processes in the visual cortex.

Findings

Effective edge detection performance on boundary datasets

Novel fusion operators improve primitive combination

Model aligns with neural behavior in early visual cortex

Abstract

It is known that the human visual system performs a hierarchical information process in which early vision cues (or primitives) are fused in the visual cortex to compose complex shapes and descriptors. While different aspects of the process have been extensively studied, as the lens adaptation or the feature detection, some other,as the feature fusion, have been mostly left aside. In this work we elaborate on the fusion of early vision primitives using generalizations of the Choquet integral, and novel aggregation operators that have been extensively studied in recent years. We propose to use generalizations of the Choquet integral to sensibly fuse elementary edge cues, in an attempt to model the behaviour of neurons in the early visual cortex. Our proposal leads to a full-framed edge detection algorithm, whose performance is put to the test in state-of-the-art boundary detection datasets.