English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Printed Mathematical expression recognition (PMER) aims to transcribe aprinted mathematical expression image into a structural expression, such asLaTeX expression. It is a crucial task for many applications, includingautomatic question recommendation, automatic problem solving and analysis ofthe students, etc. Currently, the mainstream solutions rely on solving imagecaptioning tasks, all addressing image summarization. As such, these methodscan be suboptimal for solving MER problem.  In this paper, we propose a new method named EDSL, shorted forencoder-decoder with symbol-level features, to identify the printedmathematical expressions from images. The symbol-level image encoder of EDSLconsists of segmentation module and reconstruction module. By performingsegmentation module, we identify all the symbols and their spatial informationfrom images in an unsupervised manner. We then design a novel reconstructionmodule to recover the symbol dependencies after symbol segmentation.Especially, we employ a position correction attention mechanism to capture thespatial relationships between symbols. To alleviate the negative impact fromlong output, we apply the transformer model for transcribing the encoded imageinto the sequential and structural output. We conduct extensive experiments ontwo real datasets to verify the effectiveness and rationality of our proposedEDSL method. The experimental results have illustrated that EDSL has achieved92.7\% and 89.0\% in evaluation metric Match, which are 3.47\% and 4.04\%higher than the state-of-the-art method. Our code and datasets are available athttps://github.com/abcAnonymous/EDSL .

EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition