Modelling curvature of a bent paper leaf
This work suggests a potential incremental improvement for computer vision tasks by offering an alternative method to neural networks.
The authors explored using algebraic geometry to model the curvature of a bent paper leaf, proposing it as a fast alternative to neural networks for feature extraction on manifolds.
In this article, we briefly describe various tools and approaches that algebraic geometry has to offer to straighten bent objects. Throughout this article we will consider a specific example of a bent or curved piece of paper which in our case acts very much like an elastica curve. We conclude this article with a suggestion to algebraic geometry as a viable and fast performance alternative of neural networks in vision and machine learning. The purpose of this article is not to build a full blown framework but to show possibility of using algebraic geometry as an alternative to neural networks for recognizing or extracting features on manifolds.