Component tree loss function: definition and optimization

DOI10.1007/978-3-031-19897-7_20MaRDI QIDQ6103054zbMATH OpenFDO

Authors Benjamin Perret, Jean Cousty

Publication date 2 June 2023

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2101.08063

zbMATH Keywords

connected filterscontinuous optimizationmathematical morphologymax-treetopological loss

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10)

Abstract: In this article, we propose a method to design loss functions based on component trees which can be optimized by gradient descent algorithms and which are therefore usable in conjunction with recent machine learning approaches such as neural networks. We show how the altitudes associated to the nodes of such hierarchical image representations can be differentiated with respect to the image pixel values. This feature is used to design a generic loss function that can select or discard image maxima based on various attributes such as extinction values. The possibilities of the proposed method are demonstrated on simulated and real image filtering.

Recommendations

• Component-trees and multivalued images: structural properties
• The tree of shapes of an image
• Component-hypertrees for image segmentation
• Component-graph construction
• Component-Trees and Multi-value Images: A Comparative Study

Cites work

• A quasi-linear algorithm to compute the tree of shapes of \(n\)D images
• An equivalence relation between morphological dynamics and persistent homology in 1D
• Evaluation of Hierarchical Watersheds
• Improved detection of faint extended astronomical objects through statistical attribute filtering
• Incremental Algorithm for Hierarchical Minimum Spanning Forests and Saliency of Watershed Cuts
• The tree of shapes of an image
• Tree-Based Morse Regions: A Topological Approach to Local Feature Detection
• Ultrametric fitting by gradient descent ^*

Cited in

(6)

• Multivalued component tree: new results and a bridge between partial and total partition trees
• Consistent connected operators based on trees of shapes
• Hierarchy-based fuzzy segmentation and marker learning layer: theory and algorithms
• Component tree: update rather than rebuild
• Complete, compact and topological trees of shapes
• Morphological representations for learning image operators: a review

This page was built for publication: Component tree loss function: definition and optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103054)