Image Classification
Keras
English
art
File size: 6,026 Bytes
a44aa14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff08cf1
a44aa14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff08cf1
a44aa14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff08cf1
 
a44aa14
 
 
 
 
 
 
45a1db8
a44aa14
 
 
 
 
ff08cf1
 
 
 
a44aa14
45a1db8
a44aa14
 
 
 
 
 
 
 
ff08cf1
 
 
a44aa14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff08cf1
a44aa14
ff08cf1
a44aa14
ff08cf1
a44aa14
 
 
 
 
 
 
 
ff08cf1
 
a44aa14
 
ff08cf1
 
 
 
a44aa14
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff08cf1
 
a44aa14
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
# -*- coding: utf-8 -*-
"""
Created on Mon Apr 29 17:46:18 2024

@author: beni
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from PIL import Image
import os
from pylab import *
import re
from PIL import Image, ImageChops, ImageEnhance
import tensorflow as tf
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import itertools
from tensorflow.keras.utils import to_categorical 
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from tensorflow.keras.optimizers.legacy import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau, EarlyStopping
from scipy.ndimage import gaussian_filter





def convert_to_ela_image(path, quality, output_dir, resize=(256, 256)):
    filename = path
    resaved_filename = os.path.join(output_dir, os.path.splitext(os.path.basename(filename))[0] + '.resaved.jpg')
    ELA_filename = os.path.join(output_dir, os.path.splitext(os.path.basename(filename))[0] + '.ela.png')
    
    # Open and resize the image
    im = Image.open(filename).convert('RGB')
    im_resized = im.resize(resize)
    
    # Save the resized image
    im_resized.save(resaved_filename, 'JPEG', quality=quality)
    resaved_im = Image.open(resaved_filename)
    
    ela_im = ImageChops.difference(im_resized, resaved_im)
    
    extrema = ela_im.getextrema()
    max_diff = max([ex[1] for ex in extrema])
    if max_diff == 0:
        max_diff = 1
    scale = 255.0 / max_diff
    
    ela_im = ImageEnhance.Brightness(ela_im).enhance(scale)
    
    ela_im.save(ELA_filename)
    
    return ela_im


def shuffle_and_split_data(dataframe, test_size=0.2, random_state=59):
    # Shuffle the DataFrame
    shuffled_df = dataframe.sample(frac=1, random_state=random_state).reset_index(drop=True)
    
    # Split the DataFrame into train and validation sets
    train_df, val_df = train_test_split(shuffled_df, test_size=test_size, random_state=random_state)
    
    return train_df, val_df

def labeling(path_real, path_fake):
    image_paths = []
    labels = []

    for filename in os.listdir(path_real):
        image_paths.append(os.path.join(path_real, filename))
        labels.append(0)

    for filename in os.listdir(path_fake):
        image_paths.append(os.path.join(path_fake, filename))
        labels.append(1)

    dataset = pd.DataFrame({'image_path': image_paths, 'label': labels})

    return dataset


if __name__ == "__main__":
    ##############################################################
    # handling the dataset , set it and label it
    np.random.seed(22)
    tf.random.set_seed(9)

    traning_fake_folder = 'datasets/training_set/fake/'
    traning_real_folder = 'datasets/training_set/real/'


    traning_ela_output = 'datasets/training_set/ela_output/'
    traning_set = labeling(traning_real_folder, traning_fake_folder)
        

    X = []
    Y = []

    #################################################################
    # preprocess the images using ELA method and storing the output.
    
    for index, row in traning_set.iterrows():
       X.append(array(convert_to_ela_image(row[0], 90,traning_ela_output).resize((128, 128))).flatten() / 255.0)
       Y.append(row[1])

    X = np.array(X)
    Y = to_categorical(Y, 2)
    X = X.reshape(-1, 128, 128, 3)
    X_train, X_val, Y_train, Y_val = train_test_split(X, Y, test_size = 0.2, random_state=1,shuffle=True)


    ################################################################################
    # Cnn network creation
    model = Sequential()
    model.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'valid', 
                     activation ='relu', input_shape = (128,128,3)))
    print("Input: ", model.input_shape)
    print("Output: ", model.output_shape)

    model.add(Conv2D(filters = 32, kernel_size = (5,5),padding = 'valid', 
                     activation ='relu'))
    print("Input: ", model.input_shape)
    print("Output: ", model.output_shape)

    model.add(MaxPool2D(pool_size=(2,2)))

    model.add(Dropout(0.25))
    print("Input: ", model.input_shape)
    print("Output: ", model.output_shape)

    model.add(Flatten())
    model.add(Dense(256, activation = "relu"))
    model.add(Dropout(0.5))
    model.add(Dense(2, activation = "softmax"))

    model.summary()

    #Define optimizer .
    optimizer = RMSprop(lr=0.0005, rho=0.9, epsilon=1e-08, decay=0.0)
    #setting the model , loss func , mertics , optimizer.
    model.compile(optimizer = optimizer , loss = "categorical_crossentropy", metrics=["accuracy"])
    #setting early stopping to train faster.
    early_stopping = EarlyStopping(monitor='val_acc',
                                  min_delta=0,
                                  patience=2,
        verbose=0, mode='auto')
    
    
    epochs = 22
    batch_size = 100
    #####################################################
    #running the model , adding the validation set
    history = model.fit(X_train, Y_train, batch_size = batch_size, epochs = epochs, 
              validation_data = (X_val, Y_val), verbose = 2, callbacks=[early_stopping])


    #####################################################
    #plots and metrics
    plt.plot(history.history['accuracy'])
    plt.plot(history.history['val_accuracy'])
    plt.title('Model accuracy')
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.legend(['Train', 'Validation'], loc='upper left')
    plt.show()

    # Plot training & validation loss values
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.legend(['Train', 'Validation'], loc='upper left')
    plt.show()

# every training can give different results , you can mark the next line as comment when you got the best result running the test set.
    model.save('ELA_CNN_ART_V2.h5')