I'm somewhat new to machine learning and want to implement a manufacturing application that finds the centroid of an irregular object so that as little material as possible is removed during processing. To summarize the process--the object (imagine something like a stick) is picked up by a robot and passed through 4 scanners. The scanners create a data cloud consisting of x, y, and z points as well as "c" points which represent the intensity of the transmission received at the scanner. The goal is to find a "centroid" based on these points. Would a method like cluster analysis be a good place to start here? I feel like it should be somewhat straightforward but I'm not completely sure how to identify the best method to apply.



You must log in to answer this question.

Browse other questions tagged .