3D Non-separable Moment Invariants

被引：1

作者：

Flusser, Jan ^{[1
]}

Suk, Tomas ^{[1
]}

Bedratyuk, Leonid ^{[2
]}

Karella, Tomas ^{[1
]}

机构：

[1] Czech Acad Sci, Inst Informat Theory & Automat, Vodrenskou Vezi 4, Prague 18208 8, Czech Republic

[2] Khmelnytsky Natl Univ, Instytutska 11, UA-29016 Khmelnytsky, Ukraine

来源：

COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2023, PT I | 2023年 / 14184卷

关键词：

3D recognition; 3D rotation invariants; non-separable moments; Appell polynomials; ROTATION;

D O I：

10.1007/978-3-031-44237-7_28

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we introduce new 3D rotation moment invariants, which are composed of non-separable Appell moments. The Appell moments can be substituted directly into the 3D rotation invariants instead of the geometric moments without violating their invariance. We show that non-separable moments may outperform the separable ones in terms of recognition power and robustness thanks to a better distribution of their zero surfaces over the image space. We test the numerical properties and discrimination power of the proposed invariants on three real datasets - MRI images of human brain, 3D scans of statues, and confocal microscope images of worms.

引用

页码：295 / 305

页数：11

共 24 条

[11]

Koschutnig K., 2021, Openneuro

[12]

Long F., 2022, 3D Nuclei instance segmentation dataset of fluorescence microscopy volumes of C. elegans

[13]

Long FH, 2009, NAT METHODS, V6, P667, DOI [10.1038/NMETH.1366, 10.1038/nmeth.1366]

[14] Voxel Transformer for 3D Object Detection [J].

Mao, Jiageng ;

Xue, Yujing ;

Niu, Minzhe ;

Bai, Haoyue ;

Feng, Jiashi ;

Liang, Xiaodan ;

Xu, Hang ;

Xu, Chunjing .

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :3144-3153

[15]

Maturana D, 2015, IEEE INT C INT ROBOT, P922, DOI 10.1109/IROS.2015.7353481

[16] CNN Architectures for Geometric Transformation-Invariant Feature Representation in Computer Vision: A Review [J].

Mumuni A. ;

Mumuni F. .

SN Computer Science, 2021, 2 (5)

[17] SurfNet: Generating 3D shape surfaces using deep residual networks [J].

Sinha, Ayan ;

Unmesh, Asim ;

Huang, Qixing ;

Ramani, Karthik .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :791-800

[18] 3D rotation invariants by complex moments [J].

Suk, Tomas ;

Flusser, Jan ;

Boldys, Jiri .

PATTERN RECOGNITION, 2015, 48 (11) :3516-3526

[19]

Suk T, 2011, LECT NOTES COMPUT SC, V6855, P212, DOI 10.1007/978-3-642-23678-5_24

[20]

Wu H, 2022, Arxiv, DOI arXiv:2211.11962

← 1 2 3 →