Traditional machine vision has long been used in industrial automation systems to improve production quality by replacing manual inspection traditionally done by humans. They are designed and built to work inside a factory, in a highly controlled environment. Nowadays, there are tasks that require embedded vision systems which are highly compact, function in challenging and uncontrolled environments while still maintaining extremely low latency levels and low energy consumption (e.g., fully autonomous vehicles, real-time objects detection and tracking) . Because of this, their processing architecture is different from most traditional machine vision systems and field programmable gate arrays (FPGA) is one of two main types of processors used in embedded vision systems to date. In this project, different computer vision tasks will be implemented and tested on the FPGA ranging from basic tasks (e.g., color filtering, binary thresholding, etc.) to more advanced tasks (e.g., corner detection, edge detection, blob detection, etc.)