Detects and Recognizes text and font language in an image
Performed this analysis using The Tesseract OCR Engine.
The Project consist of following steps :
1.) The first step is a connected component analysis in which outlines of the components are stored into Blobs
2.) Blobs are organized into text lines and broken into words
3.) Recognize every word in a two-pass process
4.) A final phase resolves fuzzy spaces, and finalize text
- libtesseract (>=3.04)
- libleptonica (>=1.71)
- Cython
- Pillow
- tesserocr
- Python 2.7.0 |Anaconda 4.3.0 (64-bit)|
Tested on Ubuntu 16.04 LTS amd64 xenial image built on 2017-09-19 8-core CPU
sudo apt-get update -y
sudo apt-get upgrade -y
sudo apt-get install python-dev python-pip
sudo apt-get install tesseract-ocr-all libtesseract-dev libleptonica-dev
pip install Cython
pip install Pillow
pip install tesserocr
- Simply Clone the repository and run this command from root directory.
python ocr_itt.py -i <image_path.jpg>
$ python ocr_itt.py -i e.jpg
English
Confidence score is 78.6614583333
$ python ocr_itt.py -i h.jpg
Hindi
Confidence score is 84.2118644068
$ python ocr_itt.py -i s.jpg
Spanish
Confidence score is 69.7443609023