Title :
Neural network architectures for median filtering
Author :
Koita, R.R. ; Poonacha, P.G.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Bombay, India
Abstract :
A median filter has been implemented by using a three-layer feedforward perceptron network. A feedback architecture, using the thresholding and stacking property of the median filter, has also been developed. An alternative perspective to the problem of determining the median is proposed. The new approach greatly simplifies the problem and results in an architecture in which the number of nodes in the hidden layers has a quadratic dependence on the number of inputs
Keywords :
feedforward neural nets; filtering and prediction theory; feedback architecture; hidden layers; median filter; median filtering; number of nodes; quadratic dependence; stacking; three-layer feedforward perceptron network; thresholding; Filtering; Filters; Hardware; Image processing; Neural networks; Neurofeedback; Polynomials; Stacking; Very large scale integration;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227332
