Title :
Nonlinear analog networks for image smoothing and segmentation
Author :
Lumsdaine, A. ; Wyatt, J. ; Elfadel, I.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., MIT, Cambridge, MA, USA
Abstract :
Image smoothing and segmentation algorithms are frequently formulated as optimization problems. Linear and nonlinear (reciprocal) resistive networks have solutions characterized by an extremum principle. Thus, appropriately designed networks can automatically solve certain smoothing and segmentation problems in robot vision. Switched linear resistive networks and nonlinear resistive networks are considered for such tasks. Some fundamental theorems and simulation results are provided
Keywords :
analogue circuits; computer vision; computerised picture processing; nonlinear network synthesis; extremum principle; image smoothing; nonlinear resistive networks; optimization problems; resistive networks; robot vision; segmentation algorithms; switched linear resistive networks; Computer science; Computer vision; Equations; Image segmentation; Laboratories; Minimization methods; Robot vision systems; Robotics and automation; Smoothing methods; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112269
