Journal of Mathematical Imaging and Vision最新文献_第8页

Generalized Polar Coordinate Moments with Quasi Inner Product 具有拟内积的广义极坐标矩

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-10-07 DOI: 10.1007/s10851-022-01124-9

Jianwei Yang, Beibei Wang, Yuepeng Wang

引用次数: 0

Analysis of (sub-)Riemannian PDE-G-CNNs （亚）黎曼PDE-G-CNNs的分析

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-10-03 DOI: 10.48550/arXiv.2210.00935

Gijs Bellaard, Daan Bon, Gautam Pai, B. Smets, R. Duits

{"title":"Analysis of (sub-)Riemannian PDE-G-CNNs","authors":"Gijs Bellaard, Daan Bon, Gautam Pai, B. Smets, R. Duits","doi":"10.48550/arXiv.2210.00935","DOIUrl":"https://doi.org/10.48550/arXiv.2210.00935","url":null,"abstract":"Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalizes G-CNNs. PDE-G-CNNs have the core advantages that they simultaneously (1) reduce network complexity, (2) increase classification performance, and (3) provide geometric interpretability. Their implementations primarily consist of linear and morphological convolutions with kernels. In this paper, we show that the previously suggested approximative morphological kernels do not always accurately approximate the exact kernels accurately. More specifically, depending on the spatial anisotropy of the Riemannian metric, we argue that one must resort to sub-Riemannian approximations. We solve this problem by providing a new approximative kernel that works regardless of the anisotropy. We provide new theorems with better error estimates of the approximative kernels, and prove that they all carry the same reflectional symmetries as the exact ones. We test the effectiveness of multiple approximative kernels within the PDE-G-CNN framework on two datasets, and observe an improvement with the new approximative kernels. We report that the PDE-G-CNNs again allow for a considerable reduction of network complexity while having comparable or better performance than G-CNNs and CNNs on the two datasets. Moreover, PDE-G-CNNs have the advantage of better geometric interpretability over G-CNNs, as the morphological kernels are related to association fields from neurogeometry.","PeriodicalId":16196,"journal":{"name":"Journal of Mathematical Imaging and Vision","volume":"1 1","pages":"1-25"},"PeriodicalIF":2.0,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46789078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Generalised Watson Distribution on the Hypersphere with Applications to Clustering 超球上的广义Watson分布及其在聚类中的应用

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-08-18 DOI: 10.1007/s10851-022-01118-7

S. Maybank, Liu Liu, Dacheng Tao

引用次数: 0

The 2-Orthogonal and Orthogonal Radial Shape Moments for Image Representation and Recognition 用于图像表示和识别的2-正交和正交径向形状矩

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-08-16 DOI: 10.1007/s10851-022-01113-y

A. Hjouji, J. EL-Mekkaoui

引用次数: 0

Guest Editorial: Discrete Geometry and Mathematical Morphology 客座编辑：离散几何与数学形态学

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-08-12 DOI: 10.1007/s10851-022-01117-8

F. Malmberg, Joakim Lindblad, Natasa Sladoje

引用次数: 0

A Local MM Subspace Method for Solving Constrained Variational Problems in Image Recovery 图像恢复中求解约束变分问题的局部MM子空间方法

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-08-07 DOI: 10.1007/s10851-022-01112-z

É. Chouzenoux, Ségolène Martin, J. Pesquet

引用次数: 6

Video Inpainting Using Advanced Homography-based Registration Method 使用先进的基于同形图的配准方法的视频喷漆

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-07-25 DOI: 10.1007/s10851-022-01111-0

B. Janardhana Rao, Y. Chakrapani, S. Srinivas Kumar

引用次数: 0

ADMM-Based Residual Whiteness Principle for Automatic Parameter Selection in Single Image Super-Resolution Problems 基于admm的残差白度原理在单幅图像超分辨率问题中的自动参数选择

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-07-05 DOI: 10.1007/s10851-022-01110-1

M. Pragliola, L. Calatroni, A. Lanza, F. Sgallari

引用次数: 4

A practical focus on sesame allergy and a brief review of other seed allergies. 重点介绍芝麻过敏的实际情况，并简要回顾其他种子过敏症。

4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-07-01 DOI: 10.2500/jfa.2022.4.220008

Kelsey Kaman, Jeffrey M Factor

引用次数: 0

Amplitude Mean of Functional Data on S2documentclass[12pt]{minimal} usepackage{amsmath} usepackage{wasysym} usepackage{amsfonts} usepackage{amssymb} usepackage{amsbsy} usepackage{mathrsfs} usepackage{upgreek} setlength{oddsidemargin}{-69pt} begin{document}$$mathbb {S}^2$$end{document} a Amplitude Mean of Functional Data on S2documentclass[12pt]{minimal} usepackage{amsmath} usepackage{wasysym} usepackage{amsfonts} usepackage{amssymb} usepackage{amsbsy} usepackage{mathrsfs} usepackage{upgreek} setlength{oddsidemargin}{-69pt} begin{document}$$mathbb {S}^2$$end{document} a

IF 2 4区数学

Journal of Mathematical Imaging and Vision Pub Date : 2022-06-23 DOI: 10.1007/s10851-022-01109-8

Zhengwu Zhang, B. Saparbayeva

引用次数: 0