Euclidean Invariant Recognition of 2D Shapes Using Histograms of Magnitudes of Local Fourier-Mellin Descriptors

03/13/2022
by   Xinhua Zhang, et al.
3

Because the magnitude of inner products with its basis functions are invariant to rotation and scale change, the Fourier-Mellin transform has long been used as a component in Euclidean invariant 2D shape recognition systems. Yet Fourier-Mellin transform magnitudes are only invariant to rotation and scale changes about a known center point, and full Euclidean invariant shape recognition is not possible except when this center point can be consistently and accurately identified. In this paper, we describe a system where a Fourier-Mellin transform is computed at every point in the image. The spatial support of the Fourier-Mellin basis functions is made local by multiplying them with a polynomial envelope. Significantly, the magnitudes of convolutions with these complex filters at isolated points are not (by themselves) used as features for Euclidean invariant shape recognition because reliable discrimination would require filters with spatial support large enough to fully encompass the shapes. Instead, we rely on the fact that normalized histograms of magnitudes are fully Euclidean invariant. We demonstrate a system based on the VLAD machine learning method that performs Euclidean invariant recognition of 2D shapes and requires an order of magnitude less training data than comparable methods based on convolutional neural networks.

READ FULL TEXT

page 2

page 5

page 8

research
05/23/2020

Invariant 3D Shape Recognition using Predictive Modular Neural Networks

In this paper PREMONN (PREdictive MOdular Neural Networks) model/archite...
research
06/08/2023

Representing and Learning Functions Invariant Under Crystallographic Groups

Crystallographic groups describe the symmetries of crystals and other re...
research
06/09/2015

Compact Shape Trees: A Contribution to the Forest of Shape Correspondences and Matching Methods

We propose a novel technique, termed compact shape trees, for computing ...
research
08/24/2023

VNI-Net: Vector Neurons-based Rotation-Invariant Descriptor for LiDAR Place Recognition

LiDAR-based place recognition plays a crucial role in Simultaneous Local...
research
01/03/2018

Polynomial-based rotation invariant features

One of basic difficulties of machine learning is handling unknown rotati...
research
04/14/2011

Disconnected Skeleton: Shape at its Absolute Scale

We present a new skeletal representation along with a matching framework...
research
06/24/2018

Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network

Recent work by Cohen et al. has achieved state-of-the-art results for le...

Please sign up or login with your details

Forgot password? Click here to reset