Symbol detection in online handwritten graphics using Faster R-CNN

TL;DR

This paper assesses the effectiveness of Faster R-CNN for detecting symbols in online handwritten graphics, demonstrating its potential as a general detection method across different graphic types.

Contribution

It evaluates Faster R-CNN's applicability to handwritten graphics, highlighting its versatility and analyzing various configurations for improved symbol detection.

Findings

Faster R-CNN performs effectively on flowchart and mathematical datasets.

Different network configurations impact detection accuracy and efficiency.

The method enables potential development of general graphic understanding systems.

Abstract

Symbol detection techniques in online handwritten graphics (e.g. diagrams and mathematical expressions) consist of methods specifically designed for a single graphic type. In this work, we evaluate the Faster R-CNN object detection algorithm as a general method for detection of symbols in handwritten graphics. We evaluate different configurations of the Faster R-CNN method, and point out issues relative to the handwritten nature of the data. Considering the online recognition context, we evaluate efficiency and accuracy trade-offs of using Deep Neural Networks of different complexities as feature extractors. We evaluate the method on publicly available flowchart and mathematical expression (CROHME-2016) datasets. Results show that Faster R-CNN can be effectively used on both datasets, enabling the possibility of developing general methods for symbol detection, and furthermore, general graphic understanding methods that could be built on top of the algorithm.