Sold Out
Book Categories |
I | Introduction to relational matching | |
1 | Computer Vision and Matching | |
1.1 | Correspondence problems | 1 |
1.2 | Relational matching theory | 2 |
1.3 | Organization of the thesis | 3 |
2 | A classification of matching methods | |
2.1 | Data description | 5 |
2.2 | The match evaluation function | 8 |
2.3 | Search methods | 12 |
2.4 | Hierarchy | 20 |
2.5 | Examples | 22 |
2.6 | Discussion | 32 |
3 | Formal description of relational matching | |
3.1 | Definition of relational description | 35 |
3.2 | Compositions | 37 |
3.3 | Exact matching | 38 |
3.4 | Inexact matching | 41 |
3.5 | Tree search | 42 |
3.8 | Some problems using relational matching | 43 |
4 | Problem definition and contributions of the thesis | |
4.1 | Evaluation of mappings | 45 |
4.2 | Tree search methods | 47 |
II | Theory of relational matching | |
5 | Information theory: selected topics | |
5.1 | Information measures for discrete signals | 51 |
5.2 | Information measures for continuous signals | 54 |
5.3 | The minimum description length principle | 57 |
5.4 | Discretization of continuous signals | 62 |
6 | Evaluation of mappings between relational descriptions | |
6.1 | Two traditional distance measures on graphs and relations | 67 |
6.2 | Mapping as an information channel | 69 |
6.3 | The conditional information as a distance function (after Boyer and Kak) | 73 |
6.4 | The mutual information as a merit function | 79 |
7 | Tree search methods and heuristics | |
7.1 | Problem representations in a tree | 88 |
7.2 | Tree search methods | 91 |
7.3 | Checking consistency of future instantiations | 101 |
7.4 | Unit ordering | 105 |
7.5 | The necessity of stop criteria for the correspondence problem | 107 |
III | Object location by relational matching | |
8 | Relational image and model description | |
8.1 | Image segmentation techniques | 112 |
8.2 | Extraction of image features | 115 |
8.3 | Used primitives and relations and their attributes | 121 |
9 | Evaluation functions for object location | |
9.1 | Composing the mutual information tables | 123 |
9.2 | The mutual information of the spatial resection | 134 |
9.3 | Construction of the evaluation function for object location | 135 |
9.4 | Functions for the self-diagnosis of object location | 135 |
10 | Strategy and performance of the tree search for object location | |
10.1 | Estimation of the future merit | 144 |
10.2 | Heuristics for object location | 146 |
10.3 | Description of the objects and their images | 152 |
10.4 | Performance of the object location | 155 |
11 | Summary and discussion | 163 |
Literature | 169 | |
A: Mutual information between a continuous signal and a discretized noisy observation | 181 | |
B: Distribution of the coordinates of points on a sphere | 185 | |
C: Conditional probability density function of the image line length | 187 | |
D: Tables with search results | 189 |
Login|Complaints|Blog|Games|Digital Media|Souls|Obituary|Contact Us|FAQ
CAN'T FIND WHAT YOU'RE LOOKING FOR? CLICK HERE!!! X
You must be logged in to add to WishlistX
This item is in your Wish ListX
This item is in your CollectionRelational Matching
X
This Item is in Your InventoryRelational Matching
X
You must be logged in to review the productsX
X
X
Add Relational Matching, Relational matching is a method for finding the best correspondences betweenstructural descriptions. It is widely used in computer vision for the recognition and location of objects in digital images. For this purpose, the digital images and the object mo, Relational Matching to the inventory that you are selling on WonderClubX
X
Add Relational Matching, Relational matching is a method for finding the best correspondences betweenstructural descriptions. It is widely used in computer vision for the recognition and location of objects in digital images. For this purpose, the digital images and the object mo, Relational Matching to your collection on WonderClub |