| Description |
1 online resource |
| Series |
Advances in computer vision and pattern recognition |
|
Advances in computer vision and pattern recognition.
|
| Contents |
Intro; Preface; Contents; Notations; 1 Introduction; 1.1 Examples of Pictures with Hierarchical Gestalt; 1.2 The State of the Art of Automatic Symmetry and Gestalt Recognition; 1.3 The Gestalt Domain; 1.4 Assessments for Gestalten; 1.5 Statistically Best Mean Direction or Axis; 1.6 The Structure of this Book; References; 2 Reflection Symmetry; 2.1 Introduction to Reflection Symmetric Gestalten; 2.2 The Reflection Symmetry Constraint as Defined for Extracted Primitive Objects; 2.3 Reformulation of the Constraint as a Continuous Score Function |
|
2.4 Optimal Fitting of Reflection Symmetry Aggregate Features2.5 The Role of Proximity in Evidence for Reflection Symmetry; 2.6 The Role of Similarity in Evidence for Reflection Symmetry and How to Combine the Evidences; 2.7 Nested Symmetries Reformulated as Successive Scoring on Rising Scale; 2.8 Clustering Reflection Symmetric Gestalten with Similar Axes; 2.9 The Theory of A Contrario Testing and its Application to Finding Reflection Symmetric Patches in Images; 2.10 The Minimum Description Length Approach for Nested Reflection Symmetry; 2.11 Projective Symmetry; References |
|
3 Good Continuation in Rows or Frieze Symmetry3.1 Related Work on Row Gestalt Grouping; 3.2 The Row Gestalt as Defined on Locations; 3.3 Proximity for Row Gestalten; 3.4 The Role of Similarity in Row Gestalten; 3.4.1 Vector Features; 3.4.2 Scale Features; 3.4.3 Orientation Features; 3.5 Sequential Search; 3.5.1 The Combinatorics of Row Gestalten; 3.5.2 Greedy Search for Row Prolongation; 3.6 The A Contrario Approach to Row Grouping; 3.7 Perspective Foreshortening of Rows; References; 4 Rotational Symmetry; 4.1 The Rotational Gestalt Law as Defined on Locations |
|
4.2 Fusion with Other Gestalt Laws4.2.1 Proximity Assessments for Rotational Gestalten; 4.2.2 Similarity Assessments for Rotational Gestalten; 4.3 Search for Rotational Gestalten; 4.3.1 Greedy Search for Rotational Gestalten; 4.3.2 A Practical Example with Rotational Gestalten of Level 1; 4.4 The Rotational Group and the Dihedral on Group; 4.5 Perspective Foreshortening of Rotational Gestalts; References; 5 Closure-Hierarchies of Gestalten; 5.1 Gestalt Algebra; 5.2 Empirical Experiments with Closure; 5.3 Transporting Evidence through Gestalt Algebra Terms |
|
5.3.1 Considering Additional Features5.3.2 Propagation of Adjustments through the Hierarchy; References; 6 Search; 6.1 Stratified Search; 6.2 Recursive Search; 6.3 Monte Carlo Sampling with Preferences; 6.4 Any-time Search Using a Blackboard; References; 7 Illusions; 7.1 Literature about Illusions in Seeing; 7.2 Deriving Illusion from Top-down Search; 7.3 Illusion as Tool to Counter Occlusion; References; 8 Prolongation in Good Continuation; 8.1 Related Work on Contour Chaining, Line Prolongation, and Gap Filling; 8.2 Tensor Voting |
| Summary |
This unique text/reference presents a unified approach to the formulation of Gestalt laws for perceptual grouping, and the construction of nested hierarchies by aggregation utilizing these laws. The book also describes the extraction of such constructions from noisy images showing man-made objects and clutter. Each Gestalt operation is introduced in a separate, self-contained chapter, together with application examples and a brief literature review. These are then brought together in an algebraic closure chapter, followed by chapters that connect the method to the data? i.e., the extraction of primitives from images, cooperation with machine-readable knowledge, and cooperation with machine learning. Topics and features: Offers the first unified approach to nested hierarchical perceptual grouping Presents a review of all relevant Gestalt laws in a single source Covers reflection symmetry, frieze symmetry, rotational symmetry, parallelism and rectangular settings, contour prolongation, and lattices Describes the problem from all theoretical viewpoints, including syntactic, probabilistic, and algebraic perspectives Discusses issues important to practical application, such as primitive extraction and any-time search Provides an appendix detailing a general adjustment model with constraints This work offers new insights and proposes novel methods to advance the field of machine vision, which will be of great benefit to students, researchers, and engineers active in this area. Dr.-Ing. Eckart Michaelsen is a researcher at the Object Recognition Department of Fraunhofer IOSB, Ettlingen, Germany. Dr.-Ing. Jochen Meidow is a researcher at the Scene Analysis Department of the same institution |
| Notes |
8.3 The Linear Prolongation Law and Corresponding Assessment Functions |
|
Online resource; title from digital title page (viewed on February 14, 2019) |
| Subject |
Pattern recognition systems.
|
|
Pattern recognition systems
|
| Form |
Electronic book
|
| Author |
Meidow, Jochen, author
|
| ISBN |
9783030040406 |
|
3030040402 |
|
9783030040413 |
|
3030040410 |
|
