A Scale Space Method for Volume Preserving Image Registration

2005 ◽  
pp. 561-572 ◽  
Author(s):  
Eldad Haber ◽  
Jan Modersitzki
Keyword(s):  
Image Registration ◽  
Scale Space ◽  
Volume Preserving ◽  
Space Method

Brightness Filling-in of Natural Images

Perception ◽  
1997 ◽  
Vol 26 (1_suppl) ◽  
pp. 136-136
Author(s):  
J H Elder
Keyword(s):  
Computational Model ◽  
Surface Brightness ◽  
Temporal Dynamics ◽  
Scale Space ◽  
Natural Images ◽  
Original Image ◽  
Edge Point ◽  
Contour Representation ◽  
Psychophysical Studies ◽  
Space Method

There is both psychophysical and physiological evidence that the perception of brightness variations in an image may be the result of a filling-in process in which the luminance signal is encoded only at image contours and is then neurally diffused to form representations of surface brightness. Despite this evidence, the filling-in hypothesis remains controversial. One problem is that in previous experiments highly simplified synthetic stimuli have been used; it is unclear whether brightness filling-in is feasible for complex natural images containing shading, shadows, and focal blur. To address this question, we present a computational model for brightness filling-in and results of experiments which test the model on a large and diverse set of natural images. The model is based on a scale-space method for edge detection which computes a contour code consisting of estimates of position, brightness, contrast, and blur at each edge point in an image (Elder and Zucker, 1996, paper presented at ECCV). This representation is then inverted by a diffusion-based filling-in algorithm which reconstructs an estimate of the original image. Psychophysical assessment of results shows that while filling-in of brightness alone leads to significant artifact, parallel filling-in of both brightness and blur produces perceptually accurate reconstructions. The temporal dynamics of blur reconstruction predicted by the model are consistent with psychophysical studies of blur perception (Westheimer, 1991 Journal of the Optical Society of America A8 681 – 685). These results suggest that a scale-adaptive contour representation can in principle capture the information needed for the perceptually accurate filling-in of complex natural images.

scholarly journals An adaptive inverse scale space method for compressed sensing

2012 ◽  
Vol 82 (281) ◽  
pp. 269-299 ◽  
Author(s):  
Martin Burger ◽  
Michael Möller ◽  
Martin Benning ◽  
Stanley Osher
Keyword(s):  
Compressed Sensing ◽  
Scale Space ◽  
Space Method ◽  
Inverse Scale Space

A Mathematical Morphology Based Scale Space Method for the Mining of Linear Features in Geographic Data

2006 ◽  
Vol 12 (1) ◽  
pp. 97-118 ◽  
Author(s):  
Min Wang ◽  
Yee Leung ◽  
Chenhu Zhou ◽  
Tao Pei ◽  
Jiancheng Luo
Keyword(s):  
Mathematical Morphology ◽  
Scale Space ◽  
Linear Features ◽  
Geographic Data ◽  
Space Method

Volume preserving image registration via a post-processing stage

2008 ◽  
Author(s):  
Reinhard Hameeteman ◽  
Jifke F. Veenland ◽  
Wiro J. Niessen
Keyword(s):  
Image Registration ◽  
Post Processing ◽  
Processing Stage ◽  
Volume Preserving
Sign in / Sign up

Export Citation Format

Share Document