jsfenfen / whatwordwhere
Tooling to extract data from scanned paper forms OCR-ed by Tesseract using the HOCR standard.
☆84Updated 9 years ago
Alternatives and similar repositories for whatwordwhere:
Users that are interested in whatwordwhere are comparing it to the libraries listed below
- An expandable and scalable OCR pipeline☆87Updated 7 years ago
- Docker container to provide Apache Tika RESTful API☆41Updated 9 years ago
- Demonstration of how dedupe might be used as geocoder☆17Updated 2 years ago
- code to remove "noise" from hOCR output of Tesseract OCR.☆14Updated 8 years ago
- Structured Data from PDF image-based files☆88Updated 12 years ago
- Exploring extracting tables from a PDF to CSV using PDF.JS☆103Updated 8 years ago
- Twitter visualizaton experiment using various python-based technologies.☆60Updated 8 years ago
- Using ML to extract campaign finance data from messy forms for journalism☆76Updated 2 years ago
- Next generation OCR engine based on LSTMs.☆52Updated 7 years ago
- Tools for working with Optical Character Recognition output☆16Updated 11 years ago
- A simple command line interface to the datamade/dedupe library.☆42Updated 2 years ago
- A Python web application for converting PDF forms into PDF-filling APIs☆46Updated 4 years ago
- Keyword Extraction system using Brown Clustering - (This version is trained to extract keywords from job listings)☆17Updated 10 years ago
- ☆14Updated 8 years ago
- Supervised learning for novelty detection in text☆78Updated 8 years ago
- mltk - Moz Language Tool Kit☆12Updated 10 years ago
- ArchiveKit manages data and documents during ETL processes, either on a local file system or on S3.☆15Updated 9 years ago
- Plots various graphs for a series of plaintext files in a directory☆19Updated 8 years ago
- rapid nlp prototyping☆71Updated 2 years ago
- A Python canonicalizer to disambiguate and recognize known names from a poor quality data entry list.☆20Updated 9 years ago
- Serapis is a sentence identifier and modeling pipeline / built for Wordnik☆24Updated 8 years ago
- Whippersnapper is an automated screenshot tool to keep a visual history of content on the web.☆55Updated 9 years ago
- A place to collect and share knowledge about liberating data from PDFs☆54Updated 3 years ago
- Easily crowdsource the analysis of your documents☆102Updated 7 years ago
- Extract place names from a URL or text, and add context to those names -- for example distinguishing between a country, region or city.☆62Updated 8 years ago
- Re-usable wrapper scripts for text document extractors.☆37Updated 8 years ago
- WebAnnotator is a tool for annotating Web pages. WebAnnotator is implemented as a Firefox extension (https://addons.mozilla.org/en-US/fi…☆48Updated 3 years ago
- A Python library to calculate the readability score of a text.☆139Updated 7 years ago
- Recognition Models for Kraken and CLSTM☆14Updated 5 years ago
- Extract tabular data and semantically discover it with ease! (OS)☆21Updated 9 years ago