Title :
A recurrent neural network for image flow computation
Author :
Li, Hua ; Wang, Jun
Author_Institution :
Dept. of Comput. Sci., Texas Tech Univ., Lubbock, TX, USA
Abstract :
The image flow computation in dynamic image processing can be formulated as a minimization of functionals. The authors show that this formulation can be solved by a recurrent neural network. They start with the Euler necessary condition and natural boundary condition, then derive a set of difference equations. Based on the analysis of the equations, a recurrent neural network is proposed for solving image flow. Experiments on synthetic and real laboratory image data were performed. The proposed network can be implemented in hardware
Keywords :
difference equations; image processing; motion estimation; recurrent neural nets; Euler necessary condition; aperture problem; difference equations; dynamic image processing; functional minimization; image flow; image flow computation; natural boundary condition; recurrent neural network; Apertures; Boundary conditions; Computer networks; Difference equations; Image motion analysis; Optical computing; Pixel; Recurrent neural networks; Sparse matrices; Symmetric matrices;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227317
