submission.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


#solve_captcha code
import os
import glob
from keras.models import load_model
import numpy as np
import imutils
import cv2
import pickle
import os.path
import numpy as np
import matplotlib.pyplot as plt
from imutils import paths
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.layers.core import Flatten, Dense



def resize_to_fit(image, width, height):
    """
    A helper function to resize an image to fit within a given size
    :param image: image to resize
    :param width: desired width in pixels
    :param height: desired height in pixels
    :return: the resized image
    """

    # grab the dimensions of the image, then initialize
    # the padding values
    (h, w) = image.shape[:2]

    # if the width is greater than the height then resize along
    # the width
    if w > h:
        image = imutils.resize(image, width=width)

    # otherwise, the height is greater than the width so resize
    # along the height
    else:
        image = imutils.resize(image, height=height)

    # determine the padding values for the width and height to
    # obtain the target dimensions
    padW = int((width - image.shape[1]) / 2.0)
    padH = int((height - image.shape[0]) / 2.0)

    # pad the image then apply one more resizing to handle any
    # rounding issues
    image = cv2.copyMakeBorder(image, padH, padH, padW, padW,
        cv2.BORDER_REPLICATE)
    image = cv2.resize(image, (width, height))

    # return the pre-processed image
    return image

###Prediction function


def predict(image):
    
    MODEL_FILENAME = "captcha_model.hdf5"
    MODEL_LABELS_FILENAME = "model_labels.dat"
    #CAPTCHA_IMAGE_FOLDER = "Desktop\img2"


    # Load up the model labels (so we can translate model predictions to actual letters)
    with open(MODEL_LABELS_FILENAME, "rb") as f:
        lb = pickle.load(f)

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

    # Load the image and convert it to grayscale
    # image = cv2.imread(image)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Add some extra padding around the image
    image = cv2.copyMakeBorder(image, 20, 20, 20, 20, cv2.BORDER_REPLICATE)
    plt.imshow(image)
    plt.show()
    # 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[1] if imutils.is_cv2() else 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 > 1.25:
            # This contour is too wide to be a single letter!
            # Split it in half into two letter regions!
            half_width = int(w / 2)
            letter_image_regions.append((x, y, half_width, h))
            letter_image_regions.append((x + half_width, y, half_width, h))
        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 the image instead of saving bad training data!
    #if len(letter_image_regions) != 4:
     #   continue

    # 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
    output = cv2.merge([image] * 3)
    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 - 2:y + h + 2, 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)        
        
        # draw the prediction on the output image
        cv2.rectangle(output, (x - 2, y - 2), (x + w + 4, y + h + 4), (0, 255, 0), 1)
        cv2.putText(output, letter, (x - 5, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.55, (0, 255, 0), 2)

    # Print the captcha's text
    captcha_text = "".join(predictions)
    answer=captcha_text
    #print(s)
    #print("CAPTCHA text is: {}".format(captcha_text))
    return answer

    # Show the annotated image
    #cv2.imshow("Output", output) #ERROR error: /tmp/build/80754af9/opencv_1512491966934/work/modules/highgui/src/window.cpp:611: error: (-2) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Carbon support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function cvShowImage
    #WORKAROUND https://stackoverflow.com/a/11855133/8800831
    #cv2.imwrite('workaround.jpg',output)
    #from IPython.display import Image
    #display(Image(filename='workaround.jpg'))
    
def test():
    '''
    We will be using a similar template to test your code
    '''
    image_paths = ['image2.jpeg']
    correct_answers = ['2BTX']
    score = 0

    for i,image_path in enumerate(image_paths):
        image = cv2.imread(image_path) # This input format wont change
        answer = predict(image) # a string is expected

        if correct_answers[i] == answer:
            score += 10
    
    print('The final score of the participant is',score)


if __name__ == "__main__":
    test()


# In[ ]: