solve_with_neurons.py

import sys
import os
stderr = sys.stderr
sys.stderr = open(os.devnull, 'w')
from keras.models import load_model
sys.stderr = stderr

from helpers import resize_to_fit
from imutils import paths
import numpy as np
import cv2
import pickle

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

MODEL_FILENAME = "captcha_model.hdf5"
MODEL_LABELS_FILENAME = "model_labels.dat"

with open(MODEL_LABELS_FILENAME, "rb") as f:
    lb = pickle.load(f)

# Load the trained neural network
model = load_model(MODEL_FILENAME)

model._make_predict_function()
def Solve(img_str):
    # Load the image and convert it to grayscale

    nparr = np.fromstring(img_str, np.uint8)
    image = cv2.imdecode(nparr, cv2.IMREAD_COLOR) # cv2.IMREAD_COLOR in OpenCV 3.1

    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Add some extra padding around the image
    image = cv2.copyMakeBorder(image, 20, 20, 20, 20, cv2.BORDER_CONSTANT, value=(255,255,255))

    # threshold the image (convert it to pure black and white)
    thresh = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]

    # find the contours (continuous blobs of pixels) the image
    contours = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # Hack for compatibility with different OpenCV versions
    contours = contours[0]

    letter_image_regions = []

    # Now we can loop through each of the four contours and extract the letter
    # inside of each one
    for contour in contours:
        # Get the rectangle that contains the contour
        (x, y, w, h) = cv2.boundingRect(contour)

        # Compare the width and height of the contour to detect letters that
        # are conjoined into one chunk
        if w / h > 1.7:
            # This contour is too wide to be a single letter!
            # Split it in half into two letter regions!
            return(False)
        else:
            # This is a normal letter by itself
            letter_image_regions.append((x, y, w, h))

    # If we found more or less than 4 letters in the captcha, our letter extraction
    # didn't work correcly.Skip rather than wating 5 seconds
    if len(letter_image_regions) != 5:
        return(False)

    # Sort the detected letter images based on the x coordinate to make sure
    # we are processing them from left-to-right so we match the right image
    # with the right letter
    letter_image_regions = sorted(letter_image_regions, key=lambda x: x[0])

    # Create an output image and a list to hold our predicted letters
    predictions = []

    # loop over the lektters
    for letter_bounding_box in letter_image_regions:
        # Grab the coordinates of the letter in the image
        x, y, w, h = letter_bounding_box

        # Extract the letter from the original image with a 2-pixel margin around the edge
        letter_image = image[y - 6:y + h + 6, x - 2:x + w + 2]

        # Re-size the letter image to 20x20 pixels to match training data
        letter_image = resize_to_fit(letter_image, 20, 20)

        # Turn the single image into a 4d list of images to make Keras happy
        letter_image = np.expand_dims(letter_image, axis=2)
        letter_image = np.expand_dims(letter_image, axis=0)

        # Ask the neural network to make a prediction
        prediction = model.predict(letter_image)

        # Convert the one-hot-encoded prediction back to a normal letter
        letter = lb.inverse_transform(prediction)[0]
        predictions.append(letter)

    # Print the captcha's text
    captcha_text = "".join(predictions)
    return(captcha_text)