Title :
Using LMS trees for imaging processing
Author :
Sanger, Terence D.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., MIT, Cambridge, MA, USA
Abstract :
LMS (least mean squares) trees are applied to image coding and image filtering tasks. The ability of these trees to handle high-dimensional input makes them appropriate for image processing, in which large numbers of inputs may be required even for simple tasks. A tree pruning method for increasing the forward propagation speed of the networks is proposed based on recursively eliminating subtrees with small weights
Keywords :
encoding; filtering and prediction theory; least squares approximations; picture processing; trees (mathematics); LMS trees; forward propagation speed; high-dimensional input; image coding; image filtering; imaging processing; least mean squares; recursive subtree elimination; tree pruning method; weights; Additives; Filtering; Image processing; Least squares approximation; Pixel;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155367
