Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mayank4490/OCR-plus-plus
https://github.com/mayank4490/OCR-plus-plus
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/mayank4490/OCR-plus-plus
- Owner: mayank4490
- Created: 2018-01-11T04:41:38.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2018-01-11T04:55:56.000Z (over 6 years ago)
- Last Synced: 2024-01-16T02:48:19.221Z (5 months ago)
- Language: CSS
- Size: 5.4 MB
- Stars: 5
- Watchers: 7
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Lists
- awesome-ocr - OCR++
- awesome-ocr - OCR++
README
# OCR++ : A Framework to extract information from Scholarly Articles
NOTE : The tool works only on Linux-based systems
##### Installation :
- Install the dependencies.
- Clone this repo and copy the OCR++ folder in **/var/www/html** and make a directory named "**media**" in **/var/www/html**
```sh
git clone https://github.com/ocrplusplus/ocrplusplus
cd ocrplusplus
mkdir -p /var/www/html/media
mkdir -p /var/www/html/media/documents
cp -r OCR++ /var/www/html/
```##### Usage:
- ###### With localhost as server :
- Run the following commands :
```sh
cd /var/www/html/OCR++
python manage.py runserver
```
- Now open a web-browser and go to **127.0.0.1:8000/home**
- ###### Without a server :
- Rename and cpoy the pdf as "**input.pdf**" on which you want to run OCR++ in the given directory using the command
```sh
cp path/to/pdf /var/www/html/OCR++/myproject/media/documents/input.pdf
```
- run the OCR++ engine by running the Script
```sh
cd /var/www/html/OCR++/myproject/media/documents/
python main_script_batch.py
```##### Dependencies:
- nltk (maxent_pos_tagger + averaged_perceptron_tagger)
- django <=v1.8
- crfpp (Try downloading the source from http://www.filewatcher.com/m/CRF++-0.58.tar.gz.790570-0.html)