“Gone are the days of pure mathematical approaches to solve a vision problem, now that AI has made its foray” — this could be one of the most misleading thoughts of a Deep Learning practitioner, oblivious of traditional computer vision techniques. If you are one among, then here is an attempt to make you think again.
Many of the computer vision algorithms running on the edge uses traditional math, rather than compute and memory intensive neural nets. Consider, we have scanned images containing textual content. The below attempt is to address some classical problems in scanned images, viz. skew-ness, rotation and text inversion, in a deterministic way. Feature matching and object search are also taken up using math-magic, to motivate you further.