Hase, Vaibhav J., Bhalerao, Yogesh J. ORCID: https://orcid.org/0000-0002-0743-8633, Nagarkar, Mahesh P. and Jadhav, Sandip N. (2021) Quantitative Performance Analysis of Hybrid Mesh Segmentation. In: 2nd EAI International Conference on Big Data Innovation for Sustainable Cognitive Computing, BDCC 2019. EAI/Springer Innovations in Communication and Computing . Springer, IND, pp. 115-141. ISBN 9783030475598
Preview |
PDF (Accepted_Manuscript)
- Accepted Version
Download (9MB) | Preview |
Abstract
This paper presents a comprehensive quantitative performance analysis of hybrid mesh segmentation algorithm. An important contribution of this proposed hybrid mesh segmentation algorithm is that it clusters facets using “facet area” as a novel mesh attribute. The method does not require to set any critical parameters for segmentation. The performance of the proposed algorithm is evaluated by comparing the proposed algorithm with the recently developed state-of-the-art algorithms in terms of coverage, time complexity, and accuracy. The experimentation results on various benchmark test cases demonstrate that Hybrid Mesh Segmentation approach does not depend on complex attributes, and outperforms the existing state-of-the-art algorithms. The simulation reveals that Hybrid Mesh Segmentation achieves a promising performance with coverage of more than 95%.
Item Type: | Book Section |
---|---|
Uncontrolled Keywords: | cad mesh model,coverage,feature recognition,hybrid mesh segmentation,interacting features,electrical and electronic engineering,computer networks and communications,information systems,health informatics ,/dk/atira/pure/subjectarea/asjc/2200/2208 |
Faculty \ School: | Faculty of Science > School of Engineering (former - to 2024) |
UEA Research Groups: | Faculty of Science > Research Groups > Materials, Manufacturing & Process Modelling |
Related URLs: | |
Depositing User: | LivePure Connector |
Date Deposited: | 03 Nov 2020 01:16 |
Last Modified: | 07 Nov 2024 12:49 |
URI: | https://ueaeprints.uea.ac.uk/id/eprint/77510 |
DOI: | 10.1007/978-3-030-47560-4_10 |
Downloads
Downloads per month over past year
Actions (login required)
View Item |