Development Of Techniques to Determine Object Shifts for PCB Board Assembly Automatic Optical Inspection (AOI)

In this study, we try to propose and implement a solution to the problems that occur in automatic optical inspection (AOI) systems where problems occur with regard to object shifts when this visual inspection process occurs so this shift causes the inspection process to be hampered. In this research work, a low-cost machine vision based on an SBC (Single Board Computer) is developed. Where Raspberry-Pi as a popular SBC offers the capability of being interfaced with a camera and of running a Linux-based operating system such as Ubuntu. These capabilities enable this board to be used to run sophisticated image processing programs for machine vision. The output of this system is to determine whether the object under inspection is accepted if the value of the shift is still below the tolerance value or rejected if the value of the shift exceeds the tolerance value. We propose a method to measure the distance of object shift using the Euclidean distance method while to determine our key points we use the Oriented Fast and Rotated BRIEF (ORB) method to recognize the object.