Proceedings 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: June 21-23, 1994, Seattle, Washington |
From inside the book
Results 1-3 of 16
Page 141
... affine transform . Here , a new framework for measuring affine transforms which cor- rectly handles the problem of corresponding deformed patches is presented . In this framework , points , lines or image brightnesses may be used to ...
... affine transform . Here , a new framework for measuring affine transforms which cor- rectly handles the problem of corresponding deformed patches is presented . In this framework , points , lines or image brightnesses may be used to ...
Page 142
... affine transforms are small . This linearization does not account for the deformation due to the affine transform . [ 1 , 2 , 10 , 11 ] ( Note that [ 10 ] essentially re - discovered the method due to [ 1 ] ) . 2. Matching image ...
... affine transforms are small . This linearization does not account for the deformation due to the affine transform . [ 1 , 2 , 10 , 11 ] ( Note that [ 10 ] essentially re - discovered the method due to [ 1 ] ) . 2. Matching image ...
Page 145
... affine transforming it about the center of the image . Results after the first iteration will be reported to ... transform was as [ 8 : 2.08 0.24 0.24 2.08 This shows that convergence is very rapid . The following affine transform was ...
... affine transforming it about the center of the image . Results after the first iteration will be reported to ... transform was as [ 8 : 2.08 0.24 0.24 2.08 This shows that convergence is very rapid . The following affine transform was ...
Contents
Unifying Line Processes and Robust Statistics | 15 |
Object Recognition 1 | 30 |
Feature Matching for Building Extraction from Multiple Views | 46 |
Copyright | |
86 other sections not shown
Common terms and phrases
affine transformation algorithm analysis angle approach approximation B-spline boundary camera components Computer Vision constraints coordinates corresponding curvature curve defined deformation depth derivatives described detection determined diffuse diffuse reflection direction edge eigenface equation error extracted facial filter frame function Gaussian Gaussian curvature geometric global gradient hypotheses IEEE illumination image registration indexing input invariant iteration kernel labeling light source linear matching matrix measure method minimizing module motion estimation nodes noise normal object recognition obtained optical flow optimal outliers parameters Pattern performance pixel plane points pose problem projection pyramid reconstruction recovered reflectance map regions representation robot robust rotation s-map scale scale-space scene segments sequence shape shown in Figure shows smooth solution space spatial specular specular reflection stereo structure superquadrics surface normal surface reconstruction technique texture tion vector velocity vertical viewpoint visible rim visual