OCR using microsoft cognitive - microsoft-cognitive

Question

What if i only want to process image from disk for reading text from it and storing them in text file.
As it is working for both json and data. i want to do work with data only. How to do that?
from __future__ import print_function
import time
import requests
import cv2
import operator
import numpy as np
# Import library to display results
import matplotlib.pyplot as plt
%matplotlib inline
_url = 'https://api.projectoxford.ai/vision/v1/analyses'
_key = 'd784ea882edd4feaa373dc5a80fa87e8'
_maxNumRetries = 10
def processRequest( json, data, headers, params ):
"""
Helper function to process the request to Project Oxford
Parameters:
json: Used when processing images from its URL. See API Documentation
data: Used when processing image read from disk. See API Documentation
headers: Used to pass the key information and the data type request
"""
retries = 0
result = None
while True:
response = requests.request( 'post', _url, json = json, data = data, headers = headers, params = params )
if response.status_code == 429:
print( "Message: %s" % ( response.json()['error']['message'] ) )
if retries <= _maxNumRetries:
time.sleep(1)
retries += 1
continue
else:
print( 'Error: failed after retrying!' )
break
elif response.status_code == 200 or response.status_code == 201:
if 'content-length' in response.headers and int(response.headers['content-length']) == 0:
result = None
elif 'content-type' in response.headers and isinstance(response.headers['content-type'], str):
if 'application/json' in response.headers['content-type'].lower():
result = response.json() if response.content else None
elif 'image' in response.headers['content-type'].lower():
result = response.content
else:
print( "Error code: %d" % ( response.status_code ) )
print( "Message: %s" % ( response.json()['error']['message'] ) )
break
return result
def renderResultOnImage( result, img ):
"""Display the obtained results onto the input image"""
R = int(result['color']['accentColor'][:2],16)
G = int(result['color']['accentColor'][2:4],16)
B = int(result['color']['accentColor'][4:],16)
cv2.rectangle( img,(0,0), (img.shape[1], img.shape[0]), color = (R,G,B), thickness = 25 )
if 'categories' in result:
categoryName = sorted(result['categories'], key=lambda x: x['score'])[0]['name']
cv2.putText( img, categoryName, (30,70), cv2.FONT_HERSHEY_SIMPLEX, 2, (255,0,0), 3 )
pathToFileInDisk = r'test.jpg'
with open( pathToFileInDisk, 'rb' ) as f:
data = f.read()
# Computer Vision parameters
params = { 'visualFeatures' : 'Color,Categories'}
headers = dict()
headers['Ocp-Apim-Subscription-Key'] = _key
headers['Content-Type'] = 'application/octet-stream'
json = None
result = processRequest( json, data, headers, params )
if result is not None:
# Load the original image, fetched from the URL
data8uint = np.fromstring( data, np.uint8 ) # Convert string to an unsigned int array
img = cv2.cvtColor( cv2.imdecode( data8uint, cv2.IMREAD_COLOR ), cv2.COLOR_BGR2RGB )
renderResultOnImage( result, img )
ig, ax = plt.subplots(figsize=(15, 20))
ax.imshow( img )
It's showing sytax error at %matplot inline

Answer 1

I gather you copied your Python code from somewhere, and there are a number of issues with it:
Your syntax error is stemming from the fact that %matplotlib is valid syntax for iPython, not plain Python.
Based on your problem description, IIUC, you've no need for any plotting code, so you might as well drop matplotlib (and cv2 and numpy, for that matter).
Your API URL is wrong: you want https://api.projectoxford.ai/vision/v1.0/ocr.
The code you'll want will be basically like this:
import json
import requests
import urllib
headers = {
# Request headers
'Content-Type': 'application/json',
'Ocp-Apim-Subscription-Key': 'YOUR_KEY_HERE',
}
params = urllib.urlencode({
# Request parameters
'language': 'unk',
'detectOrientation ': 'true',
})
body = {"url":"YOUR_URL_HERE"}
response = requests.post("https://api.projectoxford.ai/vision/v1.0/ocr?%s" % params, json=body, headers=headers)
result = response.json()
for region in result['regions']:
for line in region['lines']:
for word in line['words']:
print word['text']
Get more details about the response JSON on the API page, if you want, for instance, to arrange the text differently.
You forgot to redact your API key, so you'll probably want to generate a new one via the subscriptions page.