Detecting Mathematical Expressions in Scientific Document Images Using a U-Net Trained on a Diverse Dataset

Ohyama, Wataru; Suzuki, Masato; Uchida, Seiichi

doi:10.1109/access.2019.2945825

Cited by 38 publications

(24 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, DNNs have proved the outstanding performance in the recognition and detection of mathematical expressions tasks [27]- [29]. The work in [27] takes the advantages of CNNs in the detection of isolated and inline expressions in document images. A CNN architecture based on the U-net [30] is used for detecting mathematical expressions.…”

Section: B Mathematical Expression Detection 1) Mathematical Expressmentioning

confidence: 99%

“…The training and testing datasets are described in Table 3. The number of isolated and inline expressions in each page is described in Figure 9 The second one is GTDB public dataset [27]. It has recently been used for performance evaluation of researches [48].…”

Section: A Datasetmentioning

confidence: 99%

“…For traditional methods based on OCR technique, input document images are typically rendered at high resolution (around 600 dpi) [27] to prevent recognition errors. Our method detects mathematical expressions without using any OCR modules.…”

Section: ) Evaluation Of the Impact Of Image Resolution On Mathematimentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Method for Mathematical Expression Detection in Scientific Document Images

Phong

Hoang

2020

IEEE Access

View full text Add to dashboard Cite

Mathematical expressions have been widely used in scientific documents. In order to analyze the documents, automatic detection of mathematical expressions is a crucial step. The paper presents a unified system for the detection of mathematical expressions including both inline and isolated expressions in scientific document images that usually consist of heterogeneous components (e.g., figures, tables, text and expressions). In the system, a hybrid method of two stages is proposed for the effective detection of mathematical expressions. First, the layout analysis of entire document images is introduced to improve the accuracy of text line and word segmentation. Then, both isolated and inline expressions in document images are detected. Both hand-crafted and deep learning features are extensively investigated and combined to improve the detection accuracy. Furthermore, a generic performance metric is applied to evaluate the system comprehensively. The proposed method has been evaluated on two public benchmark datasets (Marmot and GTDB). The obtained accuracies of isolated and inline expressions in the Marmot dataset are 91.18% and 81.35% while those in the GTDB dataset are 89.51% and 80.20%, respectively. The performance comparison is carried out with the conventional methods to show the outstanding effectiveness of the proposed system. Moreover, extensive experiments have been performed in order to point out the effect of document image resolution and post processing techniques on mathematical expression detection. INDEX TERMS Mathematical expression detection, document analysis, machine learning, neural network, fusion technique.

show abstract

Section: B Mathematical Expression Detection 1) Mathematical Expressmentioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Method for Mathematical Expression Detection in Scientific Document Images

Phong

Hoang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The method depends on the geometrical and statistical characteristics of symbol images. The authors in Ohyama, Suzuki, and Uchida (2019) used U‐Net framework (Ronneberger, Fischer, and Brox (2015)) to detect mathematical equations in scientific document images. A method Tangent‐CFT for embedding mathematical formulas is presented in Mansouri et al (2019).…”

Section: Related Workmentioning

confidence: 99%

A neural approach for detecting inline mathematical expressions from scientific documents

et al. 2020

View full text Add to dashboard Cite

Scientific documents generally contain multiple mathematical expressions in them.Detecting inline mathematical expressions are one of the most important and challenging tasks in scientific text mining. Recent works that detect inline mathematical expressions in scientific documents have looked at the problem from an image processing perspective. There is little work that has targeted the problem from NLP perspective. Towards this, we define a few features and applied Conditional Random Fields (CRF) to detect inline mathematical expressions in scientific documents. Apart from this feature based approach, we also propose a hybrid algorithm that combines Bidirectional Long Short Term Memory networks (Bi-LSTM) and feature-based approach for this task. Experimental results suggest that this proposed hybrid method outperforms several baselines in the literature and also individual methods in the hybrid approach.

show abstract

“…Aligning words from OCR and full-text documents is challenging for several reasons. The OCR output contains various types of recognition errors, many of which involve special symbols, Greek letters like µ or sub-and superscript characters and numbers, which are particularly frequent in chemical names, formulae, and measurement units, and which are notoriously difficult for OCR (Ohyama et al, 2019). If the printed paper document is based on PDF, it usually has an explicit page layout, which is different from the way the corresponding full-text XML document is displayed in a web browser.…”

Section: Introductionmentioning

confidence: 99%

Word-Level Alignment of Paper Documents with their Electronic Full-Text Counterparts

Müller

Ghosh

Wittig

et al. 2021

Proceedings of the 20th Workshop on Biomedical Language Processing

View full text Add to dashboard Cite

We describe a simple procedure for the automatic creation of word-level alignments between printed documents and their respective full-text versions. The procedure is unsupervised, uses standard, off-the-shelf components only, and reaches an F-score of 85.01 in the basic setup and up to 86.63 when using pre-and post-processing. Potential areas of application are manual database curation (incl. document triage) and biomedical expression OCR.

show abstract

Detecting Mathematical Expressions in Scientific Document Images Using a U-Net Trained on a Diverse Dataset

Cited by 38 publications

References 32 publications

A Hybrid Method for Mathematical Expression Detection in Scientific Document Images

A Hybrid Method for Mathematical Expression Detection in Scientific Document Images

A neural approach for detecting inline mathematical expressions from scientific documents

Word-Level Alignment of Paper Documents with their Electronic Full-Text Counterparts

Contact Info

Product

Resources

About