中
Personal Profile

Paper Publications

Current position: Home > Scientific Research > Paper Publications

An end-to-end trainable system for offline handwritten chemical formulae recognition

Release Time:2026-06-30
Hits:
Date:
2026-06-30
Institution:
人工智能教育学部
Title of Paper:
An end-to-end trainable system for offline handwritten chemical formulae recognition
Journal:
Proceedings of the International Conference on Document Analysis and Recognition. International Conference on Document Analysis and Recognition
Place of Publication:
国内外公开发行
Key Words:
Character recognition ; Computer vision
Summary:
In this paper, we propose an end-to-end trainable system for recognizing handwritten chemical formulae. This system recognize once a time a chemical formula, instead of one chemical symbol or a whole chemical equation, which is in line with people's writing habits, at the same time could help to develop methods for the complicated chemical equations recognition. The proposed system adopts the CNN+RNN+CTC framework, which is one of state of the art methods in imagebased sequence labelling tasks. We extend the capability of the CNN+RNN+CTC framework to interpret 2D spatial relationships (such as 'subscript' existing in chemical formula) by introducing additional labels to represent them. The system evaluated on a self-collected data set of 12,224 samples, achieves the recognition rate of 94.98% at the chemical formula level. © 2019 IEEE.
First Author:
Liu, Xiaoxue
Correspondence Author:
张婷,余新国
Document Code:
1571043918219448320
Document Type:
00013
Page Number:
577-582
ISSN:
1520-5363
Translation or Not:
No
Date of Publication:
2019-09-25
Included Journals:
其他(ESI、Scopus、OA)、EI