Recognizing planar objects using invariant image features
This book deals with the question of how computers recognize an object irrespective of its size, position and its orientation. The basic approach is to find mathematical functions of an object's image, or of an object's \(3-D\) description, that are invariant under the transformations caused by the object's motion. The book introduces the notion of image invariants for planar objects. Major sections are as follows. The first chapter introduces features that are invariant under translation, rotation and changes in size and in contrast, with particular attention paid to the effect of using discrete images as opposed to continuous ones. Next, a tutorial introduction to the theory of algebraic invariants is presented with emphasis on moment invariants for affine transformations, and projective invariants for perspective transformations. The next two chapters are devoted entirely to affine and perspective invariants, summarizing work on both differential and global invariants. The main contribution (Chapter 6) shows how invariant features can be used to recognize objects that have been partially occluded. A treatment of the so called geometric hashing is given, followed by some methods of back projection which allow one to verify whether the hypothesized object really is in the image. Finally, a number of schemes for the use of moment invariants are presented to allow recognition under partial occlusion. A summary and conclusions close the book.
- Object recognition using algebraic and differential invariants
- scientific article; zbMATH DE number 4110157
- Invariants for Pattern Recognition and Classification
- On differential invariants of planar curves and recognizing partially occluded planar shapes
- Moments and moment invariants in pattern recognition.
- Recognition of handwritten Bengali characters: A novel multistage approach
- Invariance deformations and pattern recognition
- Combined blur and affine moment invariants and their use in pattern recognition.
- Geometric preprocessing and neurocomputing for pattern recognition and pose estimation.
- Planar numerical signature theory applied to object recognition
- On methods of improvement of the identification quality of graphical objects in geometric correlation methods
- Pose estimation of 3D free-form contours
- 3D object recognition using invariance
- scientific article; zbMATH DE number 623908 (Why is no real title available?)
- A Note on Position, Rotation and Scale Invariant Pattern Classification
- A Note on Position, Rotation and Scale Invariant Pattern Classification
- A blind definition of shape
- scientific article; zbMATH DE number 2079749 (Why is no real title available?)
- Invariants for Pattern Recognition and Classification
- scientific article; zbMATH DE number 1744973 (Why is no real title available?)
- Planar object detection under scaled orthographic projection
- scientific article; zbMATH DE number 1878346 (Why is no real title available?)
- Recognition of Blurred Pieces of Discrete Planes
- A Note on Position, Rotation and Scale Invariant Pattern Classification
- Determination of blur and affine combined invariants by normalization
- Affine invariants of an immersion of a topological space in the \(n\)-dimensional real vector space
- Object recognition using algebraic and differential invariants
- Planar classification of objects
This page was built for publication: Recognizing planar objects using invariant image features
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1308630)
