app.py

import pytesseract
import cv2
import numpy as np
from flask import Flask, request, jsonify
from flask_cors import CORS

# Initialize Flask app
app = Flask(__name__)
CORS(app)

def decode_base64_image(image_data):
    """
    Decode a Base64 image into OpenCV format.
    """
    try:
        header, encoded = image_data.split(",", 1)
        image_bytes = base64.b64decode(encoded)
        np_array = np.frombuffer(image_bytes, np.uint8)
        image = cv2.imdecode(np_array, cv2.IMREAD_COLOR)
        return image
    except Exception as e:
        return None, f"Error decoding image: {str(e)}"


def preprocess_image(image):
    """
    Preprocess the image for better OCR results.
    """
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    _, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
    return binary


@app.route('/extract-text', methods=['POST'])
def extract_text():
    """
    Extract text from an uploaded image.
    """
    try:
        data = request.json
        if "image" not in data:
            return jsonify({"error": "No image provided"}), 400

        # Decode the Base64 image
        image, error = decode_base64_image(data["image"])
        if error:
            return jsonify({"error": error}), 400

        # Preprocess the image
        preprocessed_image = preprocess_image(image)

        # Extract text using Tesseract
        text = pytesseract.image_to_string(preprocessed_image, config="--oem 3 --psm 6")
        return jsonify({"text": text}), 200
    except Exception as e:
        return jsonify({"error": str(e)}), 500


@app.route('/status', methods=['GET'])
def status():
    """
    Health check endpoint to verify the server is running.
    """
    return jsonify({"status": "Server is running"}), 200


if __name__ == '__main__':
    app.run(debug=True, host='0.0.0.0', port=5000)