Convolutional Networks for Image Processing by Coupled Oscillator Arrays
This is an incremental approach for image processing tasks, offering a hardware-friendly alternative to traditional methods.
The paper tackled the problem of performing image processing convolutions with Gabor filters by using coupled oscillator arrays, achieving synchronization to measure match quality with optimal oscillator parameters favoring a moderate Q-factor.
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.