Tesseract / app.py
DIVY118's picture
Upload app.py
e3407c4 verified
from flask import Flask, request, jsonify
import pytesseract
from pytesseract import Output
import difflib
from PIL import Image
app = Flask(__name__)
def find_text_coordinates(image_file, search_text):
image = Image.open(image_file)
d = pytesseract.image_to_data(image, output_type=Output.DICT)
n_boxes = len(d['level'])
result = []
for i in range(n_boxes):
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
if d["text"][i]:
result.append(((x, y, w, h), d["text"][i]))
arr_of_words = [i[1].lower() for i in result]
closest_match = difflib.get_close_matches(search_text, arr_of_words, n=1)
if closest_match:
for i in result:
if i[1].lower() == closest_match[0].lower():
return {"text": closest_match[0], "coordinates": {"x": i[0][0], "y": i[0][1], "width": i[0][2], "height": i[0][3]}}
return None
@app.route('/ocr', methods=['POST'])
def ocr():
if 'image' not in request.files:
return jsonify({"error": "No image file provided"}), 400
if 'text' not in request.form:
return jsonify({"error": "No text provided"}), 400
image_file = request.files['image']
search_text = request.form['text'].lower()
# Find text coordinates directly from memory
result = find_text_coordinates(image_file, search_text)
if result:
return jsonify(result)
else:
return jsonify({"error": "Text not found"}), 404
if __name__ == '__main__':
app.run()