Neuro-inspired edge feature fusion using Choquet integrals

DOI10.1016/J.INS.2021.10.016arXiv2104.10984OpenAlexW3202288348WikidataQ114167414 ScholiaQ114167414MaRDI QIDQ6139510FDOQ6139510

Humberto Bustince, Graçaliz Pereira Dimuro, Cedric Marco-Detchart, Carlos Lopez-Molina, L. De Miguel, Giancarlo Lucca

Publication date: 19 January 2024

Published in: Information Sciences (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/2104.10984

zbMATH Keywords

Choquet integraledge detectionimage processingfeature extraction\(C_F\)-integralre-aggregation functions

Mathematics Subject Classification ID

Numerical smoothing, curve fitting (65D10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Cites Work

• Title not available (Why is that?)
• Associative functions. Triangular norms and copulas
• Title not available (Why is that?)
• Overlap functions
• Theory of capacities
• New results on overlap and grouping functions
• Directional monotonicity of fusion functions
• \(d\)-Choquet integrals: Choquet integrals based on dissimilarities
• Edge detection in multispectral images
• A framework for edge detection based on relief functions
• A gravitational approach to edge detection based on triangular norms
• Noise-robust edge detector combining isotropic and anisotropic Gaussian kernels
• A biologically motivated multiresolution approach to contour detection
• \(C_F\)-integrals: a new family of pre-aggregation functions with application to fuzzy rule-based classification systems

Cited In (3)

• Directional monotonicity of multidimensional fusion functions with respect to admissible orders
• \(\mathscr{QL}\)-(operators) implications derived from quasi-overlap (quasi-grouping) functions and negations on bounded lattices
• Interval-valued Atanassov intuitionistic t-norms and t-conorms endowed with the usual or admissible orders

This page was built for publication: Neuro-inspired edge feature fusion using Choquet integrals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6139510)