PDFFigures 2.0

Clark, Christopher; Divvala, Santosh

doi:10.1145/2910896.2910904

Cited by 97 publications

(41 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also present a figure classification dataset namely "FigureSeer". Clark et al [22] present another method "PDFFigures 2.0" to parse and classify figures from PDF documents along with a new dataset. Siegel et al [23] present "DeepFigures" a deep neural method for detecting figures from PDF documents.…”

Section: Related Workmentioning

confidence: 99%

Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

et al. 2020

View full text Add to dashboard Cite

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922, respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features.

show abstract

Section: Related Workmentioning

confidence: 99%

Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…First, a variety of natural language processing (NLP) approaches has been proposed [3,[5][6][7][8]. Second, computer vision systems have been developed which extract information from figures and graphics [9,10]. An NLP-based tool that deals directly with SEMs is presented by Bong et al [1].…”

Section: Related Researchmentioning

confidence: 99%

“…These tools are capable of extracting captions, references and other literature meta information; however, they cannot recognize and extract whole figures or tables from a paper. Other researchers use handcrafted features or heuristics to segment different parts of a PDF file and leverage the information contained in figures and tables [10,13]. More recent approaches try to utilize deep learning techniques like CNNs and pixel-wise segmentation for this task [9,14].…”

Section: Related Researchmentioning

confidence: 99%

Using CNNs to Detect Graphical Representations of Structural Equation Models in IS Papers

Genz¹,

Funk

2020

WI2020 Zentrale Tracks

View full text Add to dashboard Cite

Literature reviews are an essential but time-consuming part of every research endeavor and play an important role in the quality of the research findings. Traditional tools and literature databases only make use of the textual information and do not consider graphical representations like figures of structural equation models (SEMs). These models are often used in empirical studies to visualize theoretical models and key results. We design and implement an application for image recognition to simplify the search for relevant papers, by automatically recognizing SEM figures in scientific papers stored as PDF files. To classify whether a page in a paper contains an SEM figure we make use of convolutional neural networks and achieve an F 1 score of 98,7% together with a recall of 100% for the SEM class. We further describe how we intend to automatically extract information from these SEM figures.

show abstract

“…More recent methods, typically based on multiple domain-specific heuristic rules, have been developed for specific research areas, such as high-energy physics ( PDFPlotExtractor , Praczyk et al , 2013) and computer science ( pdffigures2 , Clark and Divvala, 2016). While these tools utilize clustering and classification for separating certain types of graphics, vector graphics are often incorrectly extracted due to the complex figure and document structure.…”

Section: Introductionmentioning

confidence: 99%

Figure and caption extraction from biomedical documents

Jiang

Shatkay

2019

Bioinformatics

View full text Add to dashboard Cite

MotivationFigures and captions convey essential information in biomedical documents. As such, there is a growing interest in mining published biomedical figures and in utilizing their respective captions as a source of knowledge. Notably, an essential step underlying such mining is the extraction of figures and captions from publications. While several PDF parsing tools that extract information from such documents are publicly available, they attempt to identify images by analyzing the PDF encoding and structure and the complex graphical objects embedded within. As such, they often incorrectly identify figures and captions in scientific publications, whose structure is often non-trivial. The extraction of figures, captions and figure-caption pairs from biomedical publications is thus neither well-studied nor yet well-addressed.ResultsWe introduce a new and effective system for figure and caption extraction, PDFigCapX. Unlike existing methods, we first separate between text and graphical contents, and then utilize layout information to effectively detect and extract figures and captions. We generate files containing the figures and their associated captions and provide those as output to the end-user.We test our system both over a public dataset of computer science documents previously used by others, and over two newly collected sets of publications focusing on the biomedical domain. Our experiments and results comparing PDFigCapX to other state-of-the-art systems show a significant improvement in performance, and demonstrate the effectiveness and robustness of our approach.Availability and implementationOur system is publicly available for use at: https://www.eecis.udel.edu/~compbio/PDFigCapX. The two new datasets are available at: https://www.eecis.udel.edu/~compbio/PDFigCapX/Downloads

show abstract

PDFFigures 2.0

Cited by 97 publications

References 6 publications

Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

Fi-Fo Detector: Figure and Formula Detection Using Deformable Networks

Using CNNs to Detect Graphical Representations of Structural Equation Models in IS Papers

Figure and caption extraction from biomedical documents

Contact Info

Product

Resources

About