GithubHelp home page GithubHelp logo

figureseer's Introduction

FigureSeer: Parsing Result-Figures in Research Papers

NB: FigureSeer is no longer being actively maintained. Code is provided for informational purposes only. If you're interested in taking over maintenance, please contact [email protected].

Introduction

FigureSeer is a system for parsing result-figures in research papers. It automatically localizes figures, classifies them, and analyses their content.

Citing FigureSeer

If you find FigureSeer useful in your research, please consider citing:

@inproceedings{siegelnECCV16figureseer,
    Author = {Noah Siegel and Zachary Horvitz and Roie Levin and Santosh Divvala and Ali Farhadi},
    Title = {FigureSeer: Parsing Result-Figures in Research Papers},
    Booktitle = {European Conference on Computer Vision ({ECCV})},
    Year = {2016}
}

Requirements: Software

  1. Caffe and its Matlab interface (http://caffe.berkeleyvision.org/installation.html)
  2. JSONlab (https://www.mathworks.com/matlabcentral/fileexchange/33381-jsonlab--a-toolbox-to-encode-decode-json-files)

Installation

  1. Clone the repo with git clone --recursive https://github.com/allenai/figureseer
  2. Download model weights from https://drive.google.com/corp/drive/folders/18oQ6LZbxVTH7qgEY9tj7YdstdRpr0HV_ and save them to data/models/neural-networks/.
  3. Compile pdffigures (included in the dependencies directory)
  4. In setConf.m, edit 'conf.caffeRoot' to point to your Caffe installation.
  5. Run 'main.m'

To run on your own PDFs, simply add them to figureseer/data/pdfs and run main.

Data

Data used for training models is available at the project webpage: http://allenai.org/plato/figureseer/.

License

FigureSeer is released under the GPLv2 License.

figureseer's People

Contributors

schmmd avatar siegeln avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

figureseer's Issues

Installation problems - best configuration

During installation, I've faced many problems, and one is that I can't collect Caffee's Matlab interface. Seems like it's Matlab bug and MacOS problems. Could you please as the developer recommend me the configuration which
you know for sure should work? I have MacOS 10.15 Catalina, Windows 7,
Linux Gentoo kernel version 4.19. I'd really appreciate it if you can
give me advice on the best combination of the platform, Matlab
version, and compiler, also as specify valid versions of packages so
that Figureseer can be collected and run properly?

Model weights cannot be downloaded

Hello,
I have been trying to run aws s3 cp --recursive s3://ai2-website/data/figureseer/neural-networks/ data/models/neural-networks/. However, I keep getting this error.

fatal error: An error occurred (AccessDenied) when calling the ListObjects operation: Access Denied

Although aws configure was set as below, this error does not solve.

  • AWS AccessKey ID [None]: which was created when IAM user generating.
  • AWS Secret Access Key [None]: which was created when IAM user generating.
  • Default region name [None]: us-east-1
  • Default output format [None]: json

Can I tell me how to go around this issue?

Figureseer installation problems - compilation of pdffigures

I failed here as pdffigures requires poppler, and poppler was recently updated so that
the code in pdffigures is no longer valid. I fixed "PDFUtils.cpp" and
"TextUtils.cpp", but there were still new errors. Are you going to
update the code? Is better solution to install old version of poppler?
Which should work then and what versions of other libraries are
appropriate for Figureseer?
Screen Shot 2020-05-12 at 8 05 28 PM

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.