Computer Vision Google Cloud Machine Learning

Text Recognition Using Google Cloud Vision API

You can readily use Google Cloud API to extract text from an image using Google Cloud Vision

The steps are as follows:

  • Step 1: Create a project in Google Cloud console
  • Step 2: Enable Google Cloud Vision AI
  • Step 3: Create a service account
  • Step 4: Create a service key and download the key

After that, you can open a new Google Colab file and install the Google Cloud API package

!pip install google-cloud-vision

Upload and image with text

path = r'/content/starter.jpg'

Run the following code using Google Cloud Vision API

import os, io
from google.cloud import vision
#from google.cloud.vision import types
from google.cloud.vision_v1 import types

os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'service-account.json'

def starter(path):

    client = vision.ImageAnnotatorClient()
 
    if path.startswith('http') or path.startswith('gs:'):
        image = types.Image()
        image.source.image_uri = path
    else:
        with io.open(path, 'rb') as image_file:
            content = image_file.read()
        image = types.Image(content=content)
 
    result = client.text_detection(image=image).text_annotations
 
    return result

def get_text(texts):

Output:
BUCKINGHAM PALACE
ROAD SW1
CITY OF WESTMINSTER

BUCKINGHAM
PALACE
ROAD
SW1
CITY
OF
WESTMINSTER

References:

Relevant Courses

May 30, 2021
,