Skeleton pruning by contour partitioning with discrete curve evolution.

IEEE Trans Pattern Anal Mach Intell

Department of Electronics and Information, Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China.

Published: March 2007

In this paper, we introduce a new skeleton pruning method based on contour partitioning. Any contour partition can be used, but the partitions obtained by Discrete Curve Evolution (DCE) yield excellent results. The theoretical properties and the experiments presented demonstrate that obtained skeletons are in accord with human visual perception and stable, even in the presence of significant noise and shape variations, and have the same topology as the original skeletons. In particular, we have proven that the proposed approach never produces spurious branches, which are common when using the known skeleton pruning methods. Moreover, the proposed pruning method does not displace the skeleton points. Consequently, all skeleton points are centers of maximal disks. Again, many existing methods displace skeleton points in order to produces pruned skeletons.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TPAMI.2007.59DOI Listing

Publication Analysis

Top Keywords

skeleton pruning
12
skeleton points
12
contour partitioning
8
discrete curve
8
curve evolution
8
pruning method
8
displace skeleton
8
skeleton
6
pruning contour
4
partitioning discrete
4

Similar Publications

Identifying cancer prognosis genes through causal learning.

Brief Bioinform

November 2024

School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, 130012 Changchun, China.

Accurate identification of causal genes for cancer prognosis is critical for estimating disease progression and guiding treatment interventions. In this study, we propose CPCG (Cancer Prognosis's Causal Gene), a two-stage framework identifying gene sets causally associated with patient prognosis across diverse cancer types using transcriptomic data. Initially, an ensemble approach models gene expression's impact on survival with parametric and semiparametric hazard models.

View Article and Find Full Text PDF

Objective: To investigate global optimisation of anterior acetabular column pinning channels can be achieved based on large density point cloud data.

Methods: Data were collected on the CT scans of the normal pelvis in 40 adults from January 2022 to January 2023, including 22 males and 18 females, aged 20 to 54 years old. Medical imaging data from three of the samples were selected for experimental study.

View Article and Find Full Text PDF
Article Synopsis
  • Lumbar disc herniation is a common orthopedic issue affecting movement and causing substantial back pain, which can disrupt daily life for many patients.
  • The study introduces BE-YOLOv5, an advanced model for accurately detecting lumbar disc herniation from MRI images by using a specialized dataset and enhancing the original YOLOv5 framework.
  • BE-YOLOv5 achieves a mean average precision of 89.7% and operates at 48.7 frames per second, outperforming other models like Faster R-CNN and YOLOv8 in both speed and accuracy, showing promise for effective diagnosis in clinical settings.*
View Article and Find Full Text PDF

Introduction: Primary chest wall tumors account for 5% of all thoracic neoplasms and 1% of all primary tumors. Chondrosarcoma is a rare solid tumor, with an annual incidence of <0.5 per million people per year.

View Article and Find Full Text PDF

Unlabelled: Non-pharmacological therapies, such as whole-food interventions, are gaining interest as potential approaches to prevent and/or treat low bone mineral density (BMD) in postmenopausal women. Previously, prune consumption preserved two-dimensional BMD at the total hip. Here we demonstrate that prune consumption preserved three-dimensional BMD and estimated strength at the tibia.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!