A simple tesseract python OCR done as a project for ASU 2020 for computer vision course.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
Install the requirements using the following:
pip install -r requirements.txtor if you are using python venv:
python -m venv venv
venv/Scripts/activate
pip install -r requirements.txtduplicate the .env.example and rename it to .env and fill in the tesseract_path.
you can get the list of paramters using the following:
python -m ocr --helpusage: __main__.py [-h] -i IMAGE [-c] [-t TEXT_OUTPUT_FILENAME]
[-f IMAGE_OUTPUT_FILENAME] [-v] [--getGrayScaleImage]
[--removeNoise] [--applyThresholding]
[--applyThresholdingInv] [--getDilatedImage]
[--getErodedImage] [--applyOpening] [--applyClosing]
[--getCannyResult]
A simple tesseract python script to get text from input image. by default this
list of preprocessing functions is used [getGrayScaleImage, removeNoise,
applyThresholdingInv, getDilatedImage]
optional arguments:
-h, --help show this help message and exit
-i IMAGE, --image IMAGE
path to input image
-c, --show-final-image
show the final image with an overlay of the text
recognised. (default: False)
-t TEXT_OUTPUT_FILENAME, --text-output-filename TEXT_OUTPUT_FILENAME
file name to put the text output in. (default:
output.txt)
-f IMAGE_OUTPUT_FILENAME, --image-output-filename IMAGE_OUTPUT_FILENAME
filename to output the final image in. (default:
output.png)
-v, --verbose Show intermediate images. (default: False)
--getGrayScaleImage (PreProcessing) adds getGrayScaleImage to
preprocessing. order is important.
--removeNoise (PreProcessing) adds removeNoise to preprocessing.
order is important.
--applyThresholding (PreProcessing) adds applyThresholding to
preprocessing. order is important.
--applyThresholdingInv
(PreProcessing) adds applyThresholdingInv to
preprocessing. order is important.
--getDilatedImage (PreProcessing) adds getDilatedImage to preprocessing.
order is important.
--getErodedImage (PreProcessing) adds getErodedImage to preprocessing.
order is important.
--applyOpening (PreProcessing) adds applyOpening to preprocessing.
order is important.
--applyClosing (PreProcessing) adds applyClosing to preprocessing.
order is important.
--getCannyResult (PreProcessing) adds getCannyResult to preprocessing.
order is important.
Source: https://github.com/TheDigitalPhoenixX/Simple-Tesseract-Python-OCRpy -m ocr -i "example input\input.jpg" -vinput.jpg
output.txt
This is SAMPLE TEXT
Text is at different regions
output.png
verbose:
- Visual Studio Code - Code Editor
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
We use SemVer for versioning. For the versions available, see the tags on this repository.
- Mohamed Said Sallam - Main Dev - TheDigitalPhoenixX
See also the list of contributors who participated in this project and their work in CONTRIBUTORS.md.
This project is licensed under the MIT License - see the LICENSE file for details