Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder

Guoxian Dai, Jin Xie, Fan Zhu, Yi Fang

Research output: Contribution to journalArticle

Abstract

Recent advances in 3D acquisition techniques have led to a rapid increase in the size of database of three dimensional (3D) models across areas as diverse as engineering, medicine and biology, etc. Therefore, developing an efficient shape retrieval method has been attracting more and more attention in recent years. In this paper, we have developed a novel learning paradigm for extracting a concise data-driven shape descriptor to address challenging issues posed by structural deformation variations and noise present in 3D models. First, we use the scale invariant heat kernel signature (SIHKS) to describe the vertex of the shape. The locality-constrained linear coding (LLC) is employed to encode each vertex of the shape to form the global shape representation. Then we develop a discriminative shape descriptor for retrieval using many-to-one encoder. Our proposed shape descriptor is extensively evaluated on three well-known benchmark datasets including McGill, SHREC’10 ShapeGoogle and SHREC’14 human. Experimental results on 3D shape retrieval demonstrate the superior performance of our proposed method over the state-of-the-art methods and is robust to large deformations.

Original languageEnglish (US)
Pages (from-to)330-338
Number of pages9
JournalPattern Recognition Letters
Volume83
DOIs
StatePublished - Nov 1 2016

Fingerprint

Medicine
Hot Temperature

Keywords

  • Deformation-invariant
  • Shape descriptor
  • Shape retrieval

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder. / Dai, Guoxian; Xie, Jin; Zhu, Fan; Fang, Yi.

In: Pattern Recognition Letters, Vol. 83, 01.11.2016, p. 330-338.

Research output: Contribution to journalArticle

@article{988e6e5ed7b94cd7ad6f42f6f3dbd2a2,
title = "Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder",
abstract = "Recent advances in 3D acquisition techniques have led to a rapid increase in the size of database of three dimensional (3D) models across areas as diverse as engineering, medicine and biology, etc. Therefore, developing an efficient shape retrieval method has been attracting more and more attention in recent years. In this paper, we have developed a novel learning paradigm for extracting a concise data-driven shape descriptor to address challenging issues posed by structural deformation variations and noise present in 3D models. First, we use the scale invariant heat kernel signature (SIHKS) to describe the vertex of the shape. The locality-constrained linear coding (LLC) is employed to encode each vertex of the shape to form the global shape representation. Then we develop a discriminative shape descriptor for retrieval using many-to-one encoder. Our proposed shape descriptor is extensively evaluated on three well-known benchmark datasets including McGill, SHREC’10 ShapeGoogle and SHREC’14 human. Experimental results on 3D shape retrieval demonstrate the superior performance of our proposed method over the state-of-the-art methods and is robust to large deformations.",
keywords = "Deformation-invariant, Shape descriptor, Shape retrieval",
author = "Guoxian Dai and Jin Xie and Fan Zhu and Yi Fang",
year = "2016",
month = "11",
day = "1",
doi = "10.1016/j.patrec.2016.04.005",
language = "English (US)",
volume = "83",
pages = "330--338",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder

AU - Dai, Guoxian

AU - Xie, Jin

AU - Zhu, Fan

AU - Fang, Yi

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Recent advances in 3D acquisition techniques have led to a rapid increase in the size of database of three dimensional (3D) models across areas as diverse as engineering, medicine and biology, etc. Therefore, developing an efficient shape retrieval method has been attracting more and more attention in recent years. In this paper, we have developed a novel learning paradigm for extracting a concise data-driven shape descriptor to address challenging issues posed by structural deformation variations and noise present in 3D models. First, we use the scale invariant heat kernel signature (SIHKS) to describe the vertex of the shape. The locality-constrained linear coding (LLC) is employed to encode each vertex of the shape to form the global shape representation. Then we develop a discriminative shape descriptor for retrieval using many-to-one encoder. Our proposed shape descriptor is extensively evaluated on three well-known benchmark datasets including McGill, SHREC’10 ShapeGoogle and SHREC’14 human. Experimental results on 3D shape retrieval demonstrate the superior performance of our proposed method over the state-of-the-art methods and is robust to large deformations.

AB - Recent advances in 3D acquisition techniques have led to a rapid increase in the size of database of three dimensional (3D) models across areas as diverse as engineering, medicine and biology, etc. Therefore, developing an efficient shape retrieval method has been attracting more and more attention in recent years. In this paper, we have developed a novel learning paradigm for extracting a concise data-driven shape descriptor to address challenging issues posed by structural deformation variations and noise present in 3D models. First, we use the scale invariant heat kernel signature (SIHKS) to describe the vertex of the shape. The locality-constrained linear coding (LLC) is employed to encode each vertex of the shape to form the global shape representation. Then we develop a discriminative shape descriptor for retrieval using many-to-one encoder. Our proposed shape descriptor is extensively evaluated on three well-known benchmark datasets including McGill, SHREC’10 ShapeGoogle and SHREC’14 human. Experimental results on 3D shape retrieval demonstrate the superior performance of our proposed method over the state-of-the-art methods and is robust to large deformations.

KW - Deformation-invariant

KW - Shape descriptor

KW - Shape retrieval

UR - http://www.scopus.com/inward/record.url?scp=84969132874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969132874&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2016.04.005

DO - 10.1016/j.patrec.2016.04.005

M3 - Article

VL - 83

SP - 330

EP - 338

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -