Search

This paper presents the competition on Offline Recognition and Spotting of Handwritten Mathematical Expressions (OffRaSHME) held at the 17th International Conference on Frontiers in Handwriting Recognition (ICFHR 2020). Handwritten Mathematical Expression Recognition (HMER) has wide potential applications and is capturing increasing attention in recent years. Previous HMER competitions mainly focused on online datasets or offline datasets that are converted from online data. In this competition, we have collected a dataset of offline handwritten mathematical expressions by scanning papers that contain expressions. Moreover, we labeled the offline dataset at symbol level, i.e., the bounding boxes of each symbol are also provided, to facilitate the research of HMER. At last, 19,749 offline handwritten mathematical expressions are collected for training, and 2,000 ones are provided for evaluating the participating systems. In the competition, 7 teams submitted 8 systems for the task of offline HMER, among which 5 systems only use the provided datasets without any extra data while 3 systems use extra data. The winner team achieved a recognition accuracy of 79.85% (without extra data) and 81.85% (with extra data) on the offline formula recognition task.

The task of multi-label classification is to predict multiple possible labels for the unseen instance. Currently the prevalence of multi-label data in daily life has stirred up a spree of research activities. But most of those established multi-label classification methods mainly focus on such issues as class imbalance, label relations and dimension compression. These methods usually have an untenable hypothesis that each instance is of equal importance for all labels, based on which an identical set of instances is used to establish the learning model for all labels. In this paper we introduce the concept of labeling-importance and work out each instance’s labeling-important degrees that are in line with the polynomial distribution. Afterwards, a relatively important set of instances is selected for each label before establishing its classification model. The superior performance of this proposed method is validated by comprehensive experiments.