Chalk Print? Feasibility of predicting the lecturer based on his/her chalk leftovers
Abstract
Penmanship has a high degree of uniqueness as exemplified by the seemingly universal use of hand signature as identifier in contracts validations and property ownerships. In this work, we demonstrate that the distinctiveness of one’s writing patterns is possibly embedded in the molding of chalk tips. Using conventional photometric stereo method, the three-dimensional surface features of chalk tips used in Math and Physics lectures are microscopically resolved. Principal component analysis and neural networks are then combined in identifying the chalk user based on the extracted topography. Results show 50.05% classification accuracy for 10 different individuals, that is four-fold higher than the 12.4% chance proportion criterion from the 369 chalk samples we have collected.