An analog hopfield network to overcome excessive smoothing in shape from shading
✍ Scribed by S. Ravindranath; U.B. Desai
- Publisher
- Elsevier Science
- Year
- 1994
- Tongue
- English
- Weight
- 677 KB
- Volume
- 331
- Category
- Article
- ISSN
- 0016-0032
No coin nor oath required. For personal study only.
✦ Synopsis
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 . 7n overcome this we propose the use of a line function depending on the gradient of the surface slope in the regularization term . For an analog line function, the SIB energy fimction is then minimized using an analog Hopfield network . For a binary line function, the SFS energy minimization problem isformulated as a combinatorial minimization problem ; the minimization is implemented using a Boltzmann machine (simulated annealing) . Simulation results are presented to substantiate our approach . urGeFrankanlnsamte00100032,9357 .W+a.W Wr6-0032(9A)Wl" 587 P' Pergaroon