Academic Thesis

Basic information

Name Tanaka Masaji
Belonging department
Occupation name
researchmap researcher code R000032686
researchmap agency Okayama University of Science

Title

Learnable CAD for Reconstructing 3D Models from Sketches

Bibliography Type

Author

Masaji Tanaka, Ryosuke Yamaoka

Summary

Inductive Learning, Sketch, Line Drawing, Reconstruction, Learning Interface
Generally sketches as line drawings are important tools for designers when they create new mechanical parts and so forth. Since decades, many methods of reconstructing solid models from sketches have been proposed. However, it was difficult for them to handle sketches including curved lines. Recently we proposed a method that could handle curved lines in sketches drawn in CAD. In the method, firstly sketch features were defined, and when a sketch was input, each sketch feature was detected and extracted repeatedly from the sketch until all lines were deleted in the sketch. After a feature was extracted from a sketch, the sketch would be broken and meaningless. Therefore, we applied our inductive learning technique for the issue. In this paper, we propose a new user interface for the learning technique by using simple CAD operations such as copy & paste, and also propose more simplified and clarified algorithm than our past methods.
CAD’17, Okayama, Japan, August 10-12, 2017

Magazine(name)

Proceedings of CAD’17

Publisher

2017 CAD Solutions, LLC, http://www.cadconferences.com

Volume

Number Of Pages

StartingPage

420

EndingPage

424

Date of Issue

2017/08

Referee

Exist

Invited

Not exist

Language

English

Thesis Type

Research papers (proceedings of international meetings)

ISSN

DOI

NAID

PMID

URL

J-GLOBAL ID

arXiv ID

ORCID Put Code

DBLP ID