## Advances in computer visionComputer vision solutions used to be very specific and difficult to adapt to different or even unforeseen situations. The current development is calling for simple to use yet robust applications that could be employed in various situations. This trend requires the reassessment of some theoretical issues in computer vision. A better general understanding of vision processes, new insights and better theories are needed. The papers selected from the conference staged in Dagstuhl in 1996 to gather scientists from the West and the former eastern-block countries address these goals and cover such fields as 2D images (scale space, morphology, segmentation, neural networks, Hough transform, texture, pyramids), recovery of 3-D structure (shape from shading, optical flow, 3-D object recognition) and how vision is integrated into a larger task-driven framework (hand-eye calibration, navigation, perception-action cycle). |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Joachim Weickert and Brahim Benhamouda | 1 |

Jos B T M Roerdink and Arnold Meijster | 21 |

Wladyslaw Skarbek | 41 |

Copyright | |

11 other sections not shown

### Common terms and phrases

affine transformation algorithm analysis anisotropy applied approach approximation autoassociative binary Block Matching camera canonical frames color complete integral complexity computer vision connected components constraint contraction kernels coordinate corresponding defined denote detection discrete disparity map distance dual graph dual quaternion edges encoding equation error FBIM Figure filter Fourier frequency function geometric algebra given global graph graph contraction grey value height hierarchical Hough transform IEEE Image Processing image velocity implementation interaction map Kalman filter layer line segments linear Mathematical Morphology matrix method motion neural node noise nonlinear object obtained occluding signal optical flow orientation parameters Pattern Recognition pixel pixel interactions plane points problem Proc processor properties pyramid reconstruction regions representation represented robot rotation sample scale-space scene semi-topological space semidiscrete solution spatial stereo structure subjective contours subnetwork subset surface symmetry techniques texture Theorem topology triangle vector visual watershed