Fast Radio Bursts (FRBs) are extra-galactic transient radio signals of great interest to astronomers. Due to their non-repeating random nature and short time duration (much less than one second), automatic and reliable detection of these events has been a significant challenge, with only 25 published detections since 2007. This research provides a toolset for simulation and distributed detection of FRBs based on well-known image processing techniques. Custom software was developed to simulate FRB events with unprecedented granularity based upon the currently known population of pulses, and represents them as colormapped intensity images. These images are operated on directly by a Generalized Hough transform approach, followed by pattern recognition and machine learning steps, which yields a binary classifier that is successful in detecting Fast Radio Burst pulse profiles. When compared to the computationally expensive traditional process known as de-dispersion, our approach enjoys the advantage of no need for iterative data transformation.