Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier

Ryo Hachiuma; Yuko Ozasa; Hideo Saito

doi:10.5220/0006153203250332

Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier

Ryo Hachiuma, Yuko Ozasa, Hideo Saito

Department of Information and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

It is known that humans recognize objects using combinations and positional relations of primitive shapes. The first step of such recognition is to recognize 3D primitive shapes. In this paper, we propose a method for primitive shape recognition using superquadric parameters with a metric learning method, large margin nearest neighbor (LMNN). Superquadrics can represent various types of primitive shapes using a single equation with few parameters. These parameters are used as the feature vector of classification. The real objects of primitive shapes are used in our experiment, and the results show the effectiveness of using LMNN for recognition based on superquadrics. Compared to the previous methods, which used k-nearest neighbors (76.5%) and Support Vector Machines (73.5%), our LMNN method has the best performance (79.5%).

Original language	English
Title of host publication	VISAPP
Editors	Francisco Imai, Alain Tremeau, Jose Braz
Publisher	SciTePress
Pages	325-332
Number of pages	8
ISBN (Electronic)	9789897582264
DOIs	https://doi.org/10.5220/0006153203250332
Publication status	Published - 2017 Jan 1
Event	12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017 - Porto, Portugal Duration: 2017 Feb 27 → 2017 Mar 1

Publication series

Name	VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume	5

Other

Other	12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017
Country	Portugal
City	Porto
Period	17/2/27 → 17/3/1

Keywords

3D shape primitives
Large margin nearest neighbor
Primitive shape recognition
Superquadrics

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.5220/0006153203250332

Fingerprint Dive into the research topics of 'Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier'. Together they form a unique fingerprint.

Cite this

Hachiuma, R., Ozasa, Y., & Saito, H. (2017). Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier. In F. Imai, A. Tremeau, & J. Braz (Eds.), VISAPP (pp. 325-332). (VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 5). SciTePress. https://doi.org/10.5220/0006153203250332

Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier. / Hachiuma, Ryo; Ozasa, Yuko; Saito, Hideo.

VISAPP. ed. / Francisco Imai; Alain Tremeau; Jose Braz. SciTePress, 2017. p. 325-332 (VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hachiuma, R, Ozasa, Y & Saito, H 2017, Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier. in F Imai, A Tremeau & J Braz (eds), VISAPP. VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, SciTePress, pp. 325-332, 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017, Porto, Portugal, 17/2/27. https://doi.org/10.5220/0006153203250332

Hachiuma R, Ozasa Y, Saito H. Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier. In Imai F, Tremeau A, Braz J, editors, VISAPP. SciTePress. 2017. p. 325-332. (VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications). https://doi.org/10.5220/0006153203250332

Hachiuma, Ryo ; Ozasa, Yuko ; Saito, Hideo. / Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier. VISAPP. editor / Francisco Imai ; Alain Tremeau ; Jose Braz. SciTePress, 2017. pp. 325-332 (VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications).

@inproceedings{0da6b8b3f4ba4af6a7858e69035194de,

title = "Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier",

abstract = "It is known that humans recognize objects using combinations and positional relations of primitive shapes. The first step of such recognition is to recognize 3D primitive shapes. In this paper, we propose a method for primitive shape recognition using superquadric parameters with a metric learning method, large margin nearest neighbor (LMNN). Superquadrics can represent various types of primitive shapes using a single equation with few parameters. These parameters are used as the feature vector of classification. The real objects of primitive shapes are used in our experiment, and the results show the effectiveness of using LMNN for recognition based on superquadrics. Compared to the previous methods, which used k-nearest neighbors (76.5%) and Support Vector Machines (73.5%), our LMNN method has the best performance (79.5%).",

keywords = "3D shape primitives, Large margin nearest neighbor, Primitive shape recognition, Superquadrics",

author = "Ryo Hachiuma and Yuko Ozasa and Hideo Saito",

year = "2017",

month = jan,

day = "1",

doi = "10.5220/0006153203250332",

language = "English",

series = "VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

publisher = "SciTePress",

pages = "325--332",

editor = "Francisco Imai and Alain Tremeau and Jose Braz",

booktitle = "VISAPP",

note = "12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017 ; Conference date: 27-02-2017 Through 01-03-2017",

}

TY - GEN

T1 - Primitive shape recognition via superquadric representation using large margin nearest neighbor classifier

AU - Hachiuma, Ryo

AU - Ozasa, Yuko

AU - Saito, Hideo

PY - 2017/1/1

Y1 - 2017/1/1

N2 - It is known that humans recognize objects using combinations and positional relations of primitive shapes. The first step of such recognition is to recognize 3D primitive shapes. In this paper, we propose a method for primitive shape recognition using superquadric parameters with a metric learning method, large margin nearest neighbor (LMNN). Superquadrics can represent various types of primitive shapes using a single equation with few parameters. These parameters are used as the feature vector of classification. The real objects of primitive shapes are used in our experiment, and the results show the effectiveness of using LMNN for recognition based on superquadrics. Compared to the previous methods, which used k-nearest neighbors (76.5%) and Support Vector Machines (73.5%), our LMNN method has the best performance (79.5%).

AB - It is known that humans recognize objects using combinations and positional relations of primitive shapes. The first step of such recognition is to recognize 3D primitive shapes. In this paper, we propose a method for primitive shape recognition using superquadric parameters with a metric learning method, large margin nearest neighbor (LMNN). Superquadrics can represent various types of primitive shapes using a single equation with few parameters. These parameters are used as the feature vector of classification. The real objects of primitive shapes are used in our experiment, and the results show the effectiveness of using LMNN for recognition based on superquadrics. Compared to the previous methods, which used k-nearest neighbors (76.5%) and Support Vector Machines (73.5%), our LMNN method has the best performance (79.5%).

KW - 3D shape primitives

KW - Large margin nearest neighbor

KW - Primitive shape recognition

KW - Superquadrics

UR - http://www.scopus.com/inward/record.url?scp=85047869187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047869187&partnerID=8YFLogxK

U2 - 10.5220/0006153203250332

DO - 10.5220/0006153203250332

M3 - Conference contribution

AN - SCOPUS:85047869187

T3 - VISIGRAPP 2017 - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

SP - 325

EP - 332

BT - VISAPP

A2 - Imai, Francisco

A2 - Tremeau, Alain

A2 - Braz, Jose

PB - SciTePress

T2 - 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2017

Y2 - 27 February 2017 through 1 March 2017

ER -