Manuel-DominguezCBG/Reading_images

To extract the text contained in a tablet that is in a png file and store this data in a pandas data frame

Installation

I recommend you set up a virtual environment if you want to use this script, so that it doesn't mess up any other python installation you've got. This is very simple to do by following the instructions here. A very condensed version is explain here. (By the way, I am working with a macOS machine and I will use Conda)

0. Go to the directory where you want to put this repo. Clone the repo with

   git repo https://github.com/Manuel-DominguezCBG/Reading_images

1. Create the environment with a command like this:

   conda create --name imaging_processing

2. Activate environment:

   conda activate imaging_processing

   This activates the virtual environment. You will need to do it every time you want to work on your code. For adittional inf click here for non-user Conda. And here for users Conda.

3. Install the required python modules. To do this, you can use the requirements.txt file from the repository. Something like:

   python3 -m pip install -r requirements.txt

   This might take a few minutes. Go and prepare a cup of tea in the mean time

4. Run the test script to verify that everything is installed and ready to go:

   python3 test_installation.py

5. Now go to the Jupyter Notebook and follow the instruction.