Record Details

AN ANALOG HOPFIELD NETWORK TO OVERCOME EXCESSIVE SMOOTHING IN SHAPE FROM SHADING

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title AN ANALOG HOPFIELD NETWORK TO OVERCOME EXCESSIVE SMOOTHING IN SHAPE FROM SHADING
 
Creator RAVINDRANATH, S
DESAI, UB
 
Description The regularization term used in the cost function of the shape from shading (SFS) problem is necessary to make the problem well-posed. However, it has the disadvantage of producing excessive smoothing of the surface even at places where the gradient of the surface slope is very high. To overcome this we propose th use of a line function depending on the gradient of the surface slope in the regularization term. For an analog line function. the SFS energy functions is then minimized using and analog Hopfield network. For a binary line function, the SFS energy minimization problem is formulated as a combinatorial minimization problem; the minimization is implemental using a Boltzmann machine (simulated annealing). Simulation results are presented to substantiate our approach.
 
Publisher PERGAMON-ELSEVIER SCIENCE LTD
 
Date 2011-08-23T11:10:31Z
2011-12-26T12:56:25Z
2011-12-27T05:45:09Z
2011-08-23T11:10:31Z
2011-12-26T12:56:25Z
2011-12-27T05:45:09Z
1994
 
Type Article
 
Identifier JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 331B(5), 587-605
0016-0032
http://dx.doi.org/10.1016/0016-0032(94)90038-8
http://dspace.library.iitb.ac.in/xmlui/handle/10054/10498
http://hdl.handle.net/10054/10498
 
Language en