Visual pattern recognition by moment invariants

  title={Visual pattern recognition by moment invariants},
  author={Ming-Kuei Hu},
  journal={IRE Trans. Inf. Theory},
  • M. Hu
  • Published 1 February 1962
  • Mathematics, Computer Science
  • IRE Trans. Inf. Theory
In this paper a theory of two-dimensional moment invariants for planar geometric figures is presented. A fundamental theorem is established to relate such moment invariants to the well-known algebraic invariants. Complete systems of moment invariants under translation, similitude and orthogonal transformations are derived. Some moment invariants under general two-dimensional linear transformations are also included. Both theoretical formulation and practical models of visual pattern recognition… 
A Method to Derive Moment Invariants
Functions of Moments that are invariant under geometric transformations are useful for image analysis and pattern recognition. The basic model of computer vision is projective transformation. Yet it
Form Recognition Using Moment Invariants for Three Dimensional Perspective Transformations
The invariant recognition of forms is important for many tasks. The purpose of this paper is to consider algebraic and moment invariants for perspective transformations. These are important because
Pattern recognition by affine moment invariants
The invariants from second- and third-order moments are derived and shown to be complete and to be invariant under general affine transformation and used for recognition of affine-deformed objects.
Detection and Comparison of Objects Using Two Dimensional Geometric Moment Invariants
In this paper, we present the concept of Moment Invariants. Objects can be detected with the help of Moment Invariants. Different Moment Invariants are discussed in this paper. The pitfalls of
n-Dimensional Moment Invariants and Conceptual Mathematical Theory of Recognition n-Dimensional Solids
It is the author's opinion that this theory is a useful step toward the essential development of robot vision and toward creating machine intelligence-to make machines able to think by means of geometric concepts of different generalities and dimensions, and by associations of these concepts.
Explicit Separable two dimensional Moment Invariants for object recognition
This paper proposes a direct approach to construct a set of discrete separable Tchebichef-Krawtchouk Moment Invariants which are simultaneously invariant to Rotation, Scaling and Translation transformation, based on the explicit form of the TcheBichef and K Rawtchouk polynomials.
An automatic method for generating affine moment invariants
A large set of invariant polynomials can be generated automatically and immediately by the algorithm designed, and these new affine moment invariants can be applied to recognize the image.
Implicit Invariants and Object Recognition
  • J. Kautsky, J. Flusser, F. Šroubek
  • Computer Science
    9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007)
  • 2007
This paper presents implicit moment invariants with respect to polynomial transform of spatial coordinates, describes their stable and efficient implementation by means of orthogonal polynomials, and demonstrates their robustness as well as performance in a real life experiment.
The curve-structure invariant moments for shape analysis and recognition
This correspondence addresses the problem of rotation, scale, and translation invariant recognition of images by introducing curve structure moment invariants based on the geometric moment invariant from transforming the density in geometric moments into a new density.
Geometric Moments and Their Invariants
  • M. Hickman
  • Computer Science, Mathematics
    Journal of Mathematical Imaging and Vision
  • 2011
This paper presents a (purely) matrix algebra approach to compute both orthogonal and affine invariants for planar objects that is ideally suited to both symbolic and numerical computation of the invariants.


Recognition of membership in classes
A geometrical approach is taken where membership in classes is regarded measurable by metrics with which a set of points, representing different members of the same class, may be brought "close" to one another.
How we know universals; the perception of auditory and visual forms.
Two neural mechanisms are described which exhibit recognition of forms. Both are independent of small perturbations at synapses of excitation, threshold, and synchrony, and are referred to partiular
Steps toward Artificial Intelligence
  • M. Minsky
  • Computer Science
    Proceedings of the IRE
  • 1961
The discussion is supported by extensive citation of the literature and by descriptions of a few of the most successful heuristic (problem-solving) programs constructed to date.
Alpha-numeric character recognition using local operations
  • J. S. Bomba
  • Computer Science
    IRE-AIEE-ACM '59 (Eastern)
  • 1959
This paper describes a demonstration of the recognition of thirty-four alpha-numeric characters through the use of the IBM 704 EDPM.
Programming pattern recognition
Everyone likes to speculate, and recently there has been a lot of talk about reading machines and hearing machines. We know it is possible to simulate speech. This raises lots of interesting
Programming pattern recognition Proc
  • Programming pattern recognition Proc