https://github.com/leha-bot/PRLib

Pre-Recognize Library - library with algorithms for improving OCR quality.
https://github.com/leha-bot/PRLib

Last synced: 3 months ago
JSON representation

Pre-Recognize Library - library with algorithms for improving OCR quality.

• Host: GitHub
• URL: https://github.com/leha-bot/PRLib
• Owner: leha-bot
• License: mit
• Created: 2017-06-03T10:18:08.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2023-05-02T18:43:36.000Z (about 1 year ago)
• Last Synced: 2024-01-16T02:48:28.466Z (5 months ago)
• Language: C++
• Size: 5.37 MB
• Stars: 88
• Watchers: 5
• Forks: 21
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-ocr - PRLib - Pre-Recognize Library - library with algorithms for improving OCR quality. (18. <a name='PreOCRProcessing'></a>Pre OCR Processing / 8.1. <a name='GroundTruth'></a>Ground Truth)
• awesome-ocr - PRLib - Pre-Recognize Library - library with algorithms for improving OCR quality. (Pre OCR Processing / CTPN [paper:2016](https://arxiv.org/pdf/1609.03605.pdf))

README

        
PRLib - Pre-Recognition Library.

The main aim of the library - prepare image for recogntion. Image processing can really help to improve recognition quality.

*Features:*

* Binarization (Global Otsu, Sauvola, Niblack, Adaptive)

* Deskew

* Denoise (Non-local Means Denoising algorithm)

* Thinning (Zhang-Suen, Guo-Hall)

* Blur detection (LAPM, LAPV, TENG, GLVN)

* Deblur (Gaussian-based)

* White balance (Simple, Grayworld)

* Border detection (Canny-based)

* Removing perspective warp

* Crop

*Dependencies:* OpenCV + OpenCV contrib, Leptonica.

*How to build:*

1) Go to the directory with source code

2) Make directory for build:

```

    mkdir build

```

3) Run cmake:

```

    cmake ..

```    

4) Run make:

```

    make

```