Dirty, ugly, and hopefully useful OCR of Facebook Papers docs released by Gizmodo

Overview

Quick and Dirty OCR of Facebook Papers

Gizmodo has been working through the Facebook Papers and releasing the docs that they process and review.

As luck would have it, I had some ugly but functional code lying around that would do a first pass on OCR on these docs. That code is in the pdf_to_image.py script. I'd welcome improvement to the code, especially in image cleanup prior to OCR (lines 92-97, approx). I experimented with cleaning up the image via PIL and cv2, but the results were less accurate, almost certainly due to my lack of familiarity with either of these approaches.

These Facebook Papers are especially challenging from an OCR perspective because many of them are pictures taken of a screen, so the base image quality isn't especially good. Because of this, not every document can be processed cleanly, and the documents that do get processed have some cruft in them.

With that said, the text pulled from these files simplifies the process of parsing through a large amount of data for keywords.

Other (Better) Options

This OCR should be seen as a first step. Text files are generally a decent starting point because they allow for a wide range of follow on analysis.

And, other/better options exist. For a comprehensive, contained analysis, these other options will almost certainly be a better choice.

Want to help?

If you want to collaborate on this project, let me know!

You might also like...
Tracking the latest progress in Scene Text Detection and Recognition: Must-read papers well organized

SceneTextPapers Tracking the latest progress in Scene Text Detection and Recognition: must-read papers well organized Information about this repositor

A curated list of papers, code and resources pertaining to image composition

A curated list of resources including papers, datasets, and relevant links pertaining to image composition.

Turn images of tables into CSV data. Detect tables from images and run OCR on the cells.
Turn images of tables into CSV data. Detect tables from images and run OCR on the cells.

Table of Contents Overview Requirements Demo Modules Overview This python package contains modules to help with finding and extracting tabular data fr

Code for the paper STN-OCR: A single Neural Network for Text Detection and Text Recognition

STN-OCR: A single Neural Network for Text Detection and Text Recognition This repository contains the code for the paper: STN-OCR: A single Neural Net

A pure pytorch implemented ocr project including text detection and recognition
A pure pytorch implemented ocr project including text detection and recognition

ocr.pytorch A pure pytorch implemented ocr project. Text detection is based CTPN and text recognition is based CRNN. More detection and recognition me

A set of workflows for corpus building through OCR, post-correction and normalisation
A set of workflows for corpus building through OCR, post-correction and normalisation

PICCL: Philosophical Integrator of Computational and Corpus Libraries PICCL offers a workflow for corpus building and builds on a variety of tools. Th

MXNet OCR implementation. Including text recognition and detection.

insightocr Text Recognition Accuracy on Chinese dataset by caffe-ocr Network LSTM 4x1 Pooling Gray Test Acc SimpleNet N Y Y 99.37% SE-ResNet34 N Y Y 9

ISI's Optical Character Recognition (OCR) software for machine-print and handwriting data
ISI's Optical Character Recognition (OCR) software for machine-print and handwriting data

VistaOCR ISI's Optical Character Recognition (OCR) software for machine-print and handwriting data Publications "How to Efficiently Increase Resolutio

Python-based tools for document analysis and OCR

ocropy OCRopus is a collection of document analysis programs, not a turn-key OCR system. In order to apply it to your documents, you may need to do so

Owner
Bill Fitzgerald
Bill Fitzgerald
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

English | 简体中文 Introduction PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and a

null 27.5k Jan 8, 2023
A collection of resources (including the papers and datasets) of OCR (Optical Character Recognition).

OCR Resources This repository contains a collection of resources (including the papers and datasets) of OCR (Optical Character Recognition). Contents

Zuming Huang 363 Jan 3, 2023
It is a image ocr tool using the Tesseract-OCR engine with the pytesseract package and has a GUI.

OCR-Tool It is a image ocr tool made in Python using the Tesseract-OCR engine with the pytesseract package and has a GUI. This is my second ever pytho

Khant Htet Aung 4 Jul 11, 2022
A little but useful tool to explore OCR data extracted with `pytesseract` and `opencv`

Screenshot OCR Tool Extracting data from screen time screenshots in iOS and Android. We are exploring 3 options: Simple OCR with no text position usin

Gabriele Marini 1 Dec 7, 2021
Indonesian ID Card OCR using tesseract OCR

KTP OCR Indonesian ID Card OCR using tesseract OCR KTP OCR is python-flask with tesseract web application to convert Indonesian ID Card to text / JSON

Revan Muhammad Dafa 5 Dec 6, 2021
Fast image augmentation library and easy to use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about library: https://www.mdpi.com/2078-2489/11/2/125

Albumentations Albumentations is a Python library for image augmentation. Image augmentation is used in deep learning and computer vision tasks to inc

null 11.4k Jan 2, 2023
A curated list of papers and resources for scene text detection and recognition

Awesome Scene Text A curated list of papers and resources for scene text detection and recognition The year when a paper was first published, includin

Jan Zdenek 43 Mar 15, 2022
Repository of conference publications and source code for first-/ second-authored papers published at NeurIPS, ICML, and ICLR.

Repository of conference publications and source code for first-/ second-authored papers published at NeurIPS, ICML, and ICLR.

Daniel Jarrett 26 Jun 17, 2021
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

EasyOCR Ready-to-use OCR with 80+ languages supported including Chinese, Japanese, Korean and Thai. What's new 1 February 2021 - Version 1.2.3 Add set

Jaided AI 16.7k Jan 3, 2023