The process of recognising printed mathematical expression consists of two general processes: symbol recognition and structural analysis which reads the expression structure and the relation between symbols within the structure, provide adequate labeling to preserve it, and finally be useful to reconstruct the whole expression.This research focused on comparing the effectivity of two correlation-based pattern matching algorithms: the well-established Sum of Squared Difference (SSD) and the relatively new Optimized Sum of Absolute Difference (OSAD) which is based on average face rather than mathing all trained symbols. Which one was better will be used on the next stage of a research on converting printed mathematical expression into LaTeX notation.. Results obtained from tests conducted shown that (1) the accuracy of OSAD is 85.6% and SSD is 70,6% on various test symbols, and (2) the usage of average face in OSAD which was proposed to reduce time needed for matching, proven to have no negative effects on its matching performance. Therefore OSAD is well ahead in processing time and accuracy than SSD.
Copyrights © 2016