Wie ich meinem Computer beigebracht habe, Dobble mit OpenCV und Deep Learning zu spielen

Wo soll ich anfangen?

Bildverarbeitung

Kontrast hinzufügen

import cv2
import imutils
imgname = 'picture1'
image = cv2.imread(f’{imgname}.jpg’)
lab = cv2.cvtColor(image, cv2.COLOR_BGR2LAB)
l, a, b = cv2.split(lab)

clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8))
cl = clahe.apply(l)
limg = cv2.merge((cl,a,b))
final = cv2.cvtColor(limg, cv2.COLOR_LAB2BGR)

Größenänderung

resized = cv2.resize(final, (800, 800))
# save the image
cv2.imwrite(f'{imgname}processed.jpg', blurred)

Karten- und Zeichenerkennung

image = cv2.imread(f’{imgname}processed.jpg’)
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
thresh = cv2.threshold(gray, 190, 255, cv2.THRESH_BINARY)[1]
# find contours
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
output = image.copy()
# draw contours on image
for c in cnts:
    cv2.drawContours(output, [c], -1, (255, 0, 0), 3)

# sort by area, grab the biggest one
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[0]
# create mask with the biggest contour
mask = np.zeros(gray.shape,np.uint8)
mask = cv2.drawContours(mask, [cnts], -1, 255, cv2.FILLED)
# card in foreground
fg_masked = cv2.bitwise_and(image, image, mask=mask)
# white background (use inverted mask)
mask = cv2.bitwise_not(mask)
bk = np.full(image.shape, 255, dtype=np.uint8)
bk_masked = cv2.bitwise_and(bk, bk, mask=mask)
# combine back- and foreground
final = cv2.bitwise_or(fg_masked, bk_masked)

# just like before (with detecting the card)
gray = cv2.cvtColor(final, cv2.COLOR_RGB2GRAY)
thresh = cv2.threshold(gray, 195, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.bitwise_not(thresh)
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:10]
# handle each contour
i = 0
for c in cnts:
    if cv2.contourArea(c) > 1000:
        # draw mask, keep contour
        mask = np.zeros(gray.shape, np.uint8)
        mask = cv2.drawContours(mask, [c], -1, 255, cv2.FILLED)
        # white background
        fg_masked = cv2.bitwise_and(image, image, mask=mask)
        mask = cv2.bitwise_not(mask)
        bk = np.full(image.shape, 255, dtype=np.uint8)
        bk_masked = cv2.bitwise_and(bk, bk, mask=mask)
        finalcont = cv2.bitwise_or(fg_masked, bk_masked)
        # bounding rectangle around contour
        output = finalcont.copy()
        x,y,w,h = cv2.boundingRect(c)
        # squares io rectangles
        if w < h:
            x += int((w-h)/2)
            w = h
        else:
            y += int((h-w)/2)
            h = w
        # take out the square with the symbol
        roi = finalcont[y:y+h, x:x+w]
        roi = cv2.resize(roi, (400,400))
        # save the symbol
        cv2.imwrite(f"{imgname}_icon{i}.jpg", roi)
        i += 1

Zeichensortierung

symbols
 ├── test
 │   ├── anchor
 │   ├── apple
 │   │   ...
 │   └── zebra
 ├── train
 │   ├── anchor
 │   ├── apple
 │   │   ...
 │   └── zebra
 └── validation
     ├── anchor
     ├── apple
     │   ...
     └── zebra

Faltungs-Training für neuronale Netze

Modellarchitektur

# imports
from keras import layers
from keras import models
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
# layers, activation layer with 57 nodes (one for every symbol)
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(400, 400, 3)))
model.add(layers.MaxPooling2D((2, 2)))  
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dropout(0.5)) 
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dense(57, activation='softmax'))
model.compile(loss='categorical_crossentropy',       optimizer=optimizers.RMSprop(lr=1e-4), metrics=['acc'])

Datenerweiterung

# specify the directories
train_dir = 'symbols/train'
validation_dir = 'symbols/validation'
test_dir = 'symbols/test'
# data augmentation with ImageDataGenerator from Keras (only train)
train_datagen = ImageDataGenerator(rescale=1./255, rotation_range=40, width_shift_range=0.1, height_shift_range=0.1, shear_range=0.1, zoom_range=0.1, horizontal_flip=True, vertical_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(train_dir, target_size=(400,400), batch_size=20, class_mode='categorical')
validation_generator = test_datagen.flow_from_directory(validation_dir, target_size=(400,400), batch_size=20, class_mode='categorical')

Modelltraining

history = model.fit_generator(train_generator, steps_per_epoch=100, epochs=100, validation_data=validation_generator, validation_steps=50)
# don't forget to save your model!
model.save('models/model.h5')

Ergebnisse

Erkennung eines gemeinsamen Symbols auf zwei Karten

• Während der Vorhersage ist etwas schiefgegangen: Es wurden keine gemeinsamen Zeichen gefunden.
• An der Kreuzung befindet sich ein Symbol (Vorhersage kann wahr oder falsch sein).
• Es gibt mehr als ein Zeichen an der Kreuzung. In diesem Fall wähle ich das Symbol mit der höchsten Wahrscheinlichkeit (den Durchschnitt beider Vorhersagen).

Fazit