arXiv · 1409.4469
Convolutional Networks for Image Processing by Coupled Oscillator Arrays
Abstract
A coupled oscillator array is shown to approximate convolutions with Gabor filters for image processing tasks. Pixelated image fragments and filter functions are converted to voltages, differenced, and input into a corresponding array of weakly coupled Voltage Controlled Oscillators (VCOs). This is referred to as Frequency Shift Keying (FSK). Upon synchronization of the array, the common node amplitude provides a metric for the degree of match between the image fragment and the filter function. The optimal oscillator parameters for synchronization are determined and favor a moderate value of the Q-factor.
Explore related subjects
Keep this discovery
Dmitri E. Nikonov, Ian A. Young, George I. Bourianoff. 2014-09-15. Convolutional Networks for Image Processing by Coupled Oscillator Arrays. https://arxiv.org/abs/1409.4469
Cite the original work for its findings. Save a collection to share your selection of sources.