How to convert an image of text into a binary view in Python using Deep Learning

To properly perform optical character recognition (OCR), a preprocessing step is required first. Generally, this involves rotating the image and converting it to a binary view, or pure black and white. There are many ways of accomplishing the latter, but the best method uses Deep Learning to enhance the quality and allow for even better accuracy. Today I’m going to show you the setup process for an API that is already equipped for just this role.

Start by installing the API client:

pip install cloudmersive-ocr-api-client

Now below you can see our code block for calling preprocessing_binarize_advanced:

from __future__ import print_function
import time
import cloudmersive_ocr_api_client
from cloudmersive_ocr_api_client.rest import ApiException
from pprint import pprint
# Configure API key authorization: Apikey
configuration = cloudmersive_ocr_api_client.Configuration()
configuration.api_key['Apikey'] = 'YOUR_API_KEY'
# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['Apikey'] = 'Bearer'
# create an instance of the API class
api_instance = cloudmersive_ocr_api_client.PreprocessingApi(cloudmersive_ocr_api_client.ApiClient(configuration))
image_file = '/path/to/file' # file | Image file to perform OCR on.  Common file formats such as PNG, JPEG are supported.
try:
# Convert an image of text into a binary (light and dark) view with ML
api_response = api_instance.preprocessing_binarize_advanced(image_file)
pprint(api_response)
except ApiException as e:
print("Exception when calling PreprocessingApi->preprocessing_binarize_advanced: %s\n" % e)

Alright, there you go! You can binarize images to your heart’s content.