A novel set of rotationally and translationally invariant features for images based on the non-commutative bispectrum

01/20/2007
by   Risi Kondor, et al.
0

We propose a new set of rotationally and translationally invariant features for image or pattern recognition and classification. The new features are cubic polynomials in the pixel intensities and provide a richer representation of the original image than most existing systems of invariants. Our construction is based on the generalization of the concept of bispectrum to the three-dimensional rotation group SO(3), and a projection of the image onto the sphere.

READ FULL TEXT

page 5

page 7

research
01/03/2018

Polynomial-based rotation invariant features

One of basic difficulties of machine learning is handling unknown rotati...
research
05/18/2011

Invariant Representative Cocycles of Cohomology Generators using Irregular Graph Pyramids

Structural pattern recognition describes and classifies data based on th...
research
06/28/2016

Facial Expression Classification Using Rotation Slepian-based Moment Invariants

Rotation moment invariants have been of great interest in image processi...
research
05/29/2013

Rotation invariants of two dimensional curves based on iterated integrals

We introduce a novel class of rotation invariants of two dimensional cur...
research
02/14/2007

Invariant template matching in systems with spatiotemporal coding: a vote for instability

We consider the design of a pattern recognition that matches templates t...
research
04/10/2017

A semidiscrete version of the Petitot model as a plausible model for anthropomorphic image reconstruction and pattern recognition

In his beautiful book [54], Jean Petitot proposes a subriemannian model ...
research
12/17/2004

Swarming around Shellfish Larvae

The collection of wild larvae seed as a source of raw material is a majo...

Please sign up or login with your details

Forgot password? Click here to reset