Related Concept Videos
Carbon Skeletons
Bone Remodeling
Bone Structure
Bone Remodeling and Repair
Virtual Work for a System of Connected Rigid Bodies
Next,...
Skeleton and Calcium Homeostasis
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
A width-independent fast thinning algorithm.
Self modulating, derivative optical spectroscopy. Part II: experimental.
Image thresholding using fuzzy entropies.
A method for improving classification reliability of multilayer perceptrons.
Design of a user friendly workstation for medical image analysis.
Acquisition and processing of audiometric data (tympanometry, stapedial reflex).
A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.
Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.
TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.
SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.
HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.
Related Experiment Video
Updated: May 29, 2026

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
Published on: April 21, 2023
From local maxima to connected skeletons.
C Arcelli1, L P Cordella, S Levialdi
1Laboratorio di Cibernetica, C. N. R., Naples, Italy.
This study introduces a parallel algorithm for generating connected skeletons from binary images. The method ensures skeleton connectivity, crucial for structural image analysis and image reconstruction.
Area of Science:
- Computer Vision
- Image Processing
- Digital Image Analysis
Background:
- Skeletonization is a key technique in digital image processing for creating simplified representations of objects.
- Connectedness of the skeleton is important for structural image descriptions but not always guaranteed by existing methods.
Purpose of the Study:
- To develop a parallel algorithm for generating connected skeletons from binary digital images.
- To ensure the generated skeleton is connected and suitable for structural image analysis.
- To enable the reconstruction of the original image from its skeleton.
Main Methods:
- A parallel algorithm that propagates the background over the image step-by-step.
- Selection of contour elements from significant convex regions or local maxima as skeleton elements.
- Investigation and resolution of disconnections that may arise during skeletonization.
Main Results:
- A novel parallel procedure for generating connected skeletons from binary images.
- The algorithm ensures the resulting skeleton is a union of simple digital arcs.
- Methods are provided to avoid disconnections, ensuring a robust skeleton.
- The inclusion of all local maxima guarantees the possibility of image recovery via reverse distance transform.
Conclusions:
- The proposed parallel algorithm effectively generates connected skeletons suitable for structural image analysis.
- The method addresses the critical issue of skeleton connectivity, enhancing its utility.
- The algorithm's ability to facilitate image reconstruction further validates its effectiveness.

