A pixel is the smallest physical unit in an image. Images contain many thousand pixels, but rarely do the edges of an object fall exactly on the boundaries of the pixel in the camera. To increase the image resolution, sub-pixel resolution is used to reliably measure the position of a line, point, or edge in an image with an accuracy that exceeds the nominal pixel resolution of the image.
Sub-pixel resolution works on the basis that a machine vision camera will give a 'grey' level value to a pixel that is partially on an edge. The darker the pixel value, the closer it is to the edge, and vice versa. Sub-pixel accuracy will convert that grey level to a partial pixel value. If you use the grey scale values of the adjacent pixels in certain mathematical relationships, you increase the resolution (sub-pixel resolution) significantly. This is a useful tool for improving the Gage Repeatability and Reproducability (Gage R&R) of vision inspection systems.
The Precision Automation Experts™ at DWFritz are skilled at utilizing machine vision in the many automated inspection systems we design and build for our our clients.