OCRFlaskAPI.py

from flask import Flask, request, jsonify
import os
import cv2
import numpy as np
import pytesseract
import csv
import re

import io
import os
import tempfile

# Imports the Google Cloud client library
from google.cloud import vision

app = Flask(__name__)

# set the path of the Google Sercice Key downloaded
os.environ[
    "GOOGLE_APPLICATION_CREDENTIALS"] = 'C:/Users/PunsisiK.LOITL-SE03/Downloads/qwiklabs-gcp-02-de13f4ddd638-843eec04eacc.json'

# Instantiates a client
client = vision.ImageAnnotatorClient()

per = 25
pixelThreshold = 500

roi = [[(300, 112), (540, 156), 'text', 'LID'],
       [(676, 112), (988, 180), 'text', 'NIC'],
       [(274, 154), (778, 236), 'text', 'Name'],
       [(278, 228), (642, 294), 'text', 'Address'],
       [(280, 292), (532, 336), 'text', 'DOB'],
       [(276, 334), (540, 384), 'text', 'D1'],
       [(274, 376), (542, 426), 'text', 'D2'],
       [(276, 420), (550, 478), 'text', 'Blood Group']]


# allow POST requests
@app.route('/OCRDL', methods=['POST'])
def faceCompare():
    data = request.get_json()
    img1 = data['img1']
    result = readData(img1)
    return jsonify(result)


def readData(img1):
    imgQ = cv2.imread('QueryImg/Drivers License.png')
    h, w, c = imgQ.shape

    orb = cv2.ORB_create(1000)
    kp1, des1 = orb.detectAndCompute(imgQ, None)

    path = 'DL'
    imgID = img1
    img = cv2.imread(path + "/" + imgID)
    kp2, des2 = orb.detectAndCompute(img, None)
    bf = cv2.BFMatcher(cv2.NORM_HAMMING)
    matches = bf.match(des2, des1)
    matches.sort(key=lambda x: x.distance)
    good = matches[:int(len(matches) * (per / 100))]

    srcPoints = np.float32([kp2[m.queryIdx].pt for m in good]).reshape(-1, 1, 2)
    dstPoints = np.float32([kp1[m.trainIdx].pt for m in good]).reshape(-1, 1, 2)

    M, _ = cv2.findHomography(srcPoints, dstPoints, cv2.RANSAC, 5.0)
    imgScan = cv2.warpPerspective(img, M, (w, h))

    # cv2.imshow(y, imgScan)
    imgShow = imgScan.copy()
    imgMask = np.zeros_like(imgShow)

    myData = []

    print(f'################## Extracting Data from Form {imgID}  ##################')

    for x, r in enumerate(roi):

        cv2.rectangle(imgMask, (r[0][0], r[0][1]), (r[1][0], r[1][1]), (0, 255, 0), cv2.FILLED)
        imgShow = cv2.addWeighted(imgShow, 0.99, imgMask, 0.1, 0)

        imgCrop = imgScan[r[0][1]:r[1][1], r[0][0]:r[1][0]]

        if r[2] == 'text':
            with tempfile.TemporaryDirectory() as tmpdirname:
                num = x + 1

                totals_file = os.path.join(tmpdirname, str(num) + '.jpg')
                cv2.imwrite(totals_file, imgCrop)

                # Loads the image into memory
                with io.open(totals_file, 'rb') as image_file:
                    content = image_file.read()
                image = vision.Image(content=content)

                response = client.text_detection(image=image)
                texts = response.text_annotations

                string = []
                for text in texts:
                    string.append(text.description)
                if len(string) != 0:
                    print(string[0])
                    myData.append(str(string[0]).replace("\n", " "))

                os.remove(totals_file)

    print("Data>>>>>>", myData)
    return myData


if __name__ == '__main__':
    app.run()