Machine Vision, Volume 1This book is an accessible and comprehensive introduction to machine vision. It provides all the necessary theoretical tools and shows how they are applied in actual image processing and machine vision systems. A key feature is the inclusion of many programming exercises that give insights into the development of practical image processing algorithms. A CD-ROM containing software and data used in these exercises is included. The book is aimed at graduate students in electrical engineering, computer science, and mathematics. It will also be a useful reference for practitioners. |
Contents
Review of mathematical principles | 8 |
Writing programs to process images | 30 |
Formation and representation | 46 |
Topic | 57 |
Linear operators and kernels | 65 |
10 | 70 |
5 | 75 |
28 | 78 |
Topic 8A Segmentation | 207 |
Shape | 216 |
Topic 9A Shape description | 240 |
Consistent labeling | 263 |
Parametric transforms | 275 |
Graphs and graphtheoretic concepts | 290 |
Image matching | 298 |
Topic 13A Matching | 312 |
10 | 85 |
Topic 5A Edge detectors | 97 |
38 | 98 |
Restoration and feature extraction | 107 |
4 | 115 |
Topic 6A Alternative and equivalent algorithms | 129 |
Mathematical morphology | 144 |
Topic 7A Morphology | 158 |
Segmentation | 181 |
Statistical pattern recognition | 326 |
Topic 14A Statistical pattern recognition | 347 |
Clustering | 356 |
Syntactic pattern recognition | 369 |
Applications | 382 |
Automatic target recognition | 392 |
| 417 | |
| 426 | |
Other editions - View all
Common terms and phrases
affine transformation algorithm Analysis and Machine annealing application approach Assignment assume axes axis Bilbro binary blur boundary brightness camera chain code chapter classifier cluster compute Computer Vision concept connected component consider contour convex coordinates corresponding curve defined denote density derivative described determine dilation dimensions distance transform edge detection edge points equation estimate example feature Fourier Gaussian gradient descent graph Hough transform IEEE Transactions illustrated in Fig Image Processing input invariant iteration labeling linear Machine Intelligence machine vision Markov matching matrix mean measure medial axis methods minimizes morphological neighbor neural network noise objective function observation optic flow optimization parameters Pattern Analysis Pattern Recognition pixel probability problem range image represent representation result sampling scale space segmentation shape simply Snyder spatial surface technique template term Texture threshold training set Transactions on Pattern V₁ vector zero