DevanagriCharacterRecognition/devanagriOCR.py at master · TusharAmbelkar/DevanagriCharacterRecognition · GitHub

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
import os
import h5py
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.models import Sequential
from keras.layers import Convolution2D,MaxPooling2D,Activation, Dropout, Flatten, Dense


trainDataGen = ImageDataGenerator(
		rotation_range = 5,
		width_shift_range = 0.1,
		height_shift_range = 0.1,
		rescale = 1.0/255,
		shear_range = 0.1,
		zoom_range = 0.1,
		horizontal_flip = False,
		fill_mode = 'nearest')

test_datagen = ImageDataGenerator(rescale=1./255)
trainGenerator = trainDataGen.flow_from_directory(
			"/home/owner/Downloads/DevanagariHandwrittenCharacterDataset/Train",
			target_size = (32,32),
			batch_size = 32,
			color_mode = "grayscale",
			class_mode = "categorical")
prev = ""
labels = ["ka","kha","ga","gha","kna","cha","chha","ja","jha","yna","t`a","t`ha","d`a","d`ha","adna","ta","tha","da","dha","na","pa","pha","ba","bha","ma","yaw","ra","la","waw","sha","shat","sa","ha","aksha","tra","gya","0","1","2","3","4","5","6","7","8","9"]
count = 0;
'''for i in trainGenerator.classes:
	if prev == labels[i]:
		count = count+1
		continue;
	print count
	print labels[i]
	count = 1
	prev = labels[i]
print count
'''

validation_generator = test_datagen.flow_from_directory(
			"/home/owner/Downloads/DevanagariHandwrittenCharacterDataset/Test",
			target_size=(32,32),
			batch_size=32,
			color_mode = "grayscale",
			class_mode= 'categorical')

model = Sequential()
model.add(Convolution2D(filters = 32,
			kernel_size = (3,3),
			strides = 1,
			activation = "relu",
			input_shape = (32,32,1)))

model.add(MaxPooling2D(pool_size=(2, 2),
			strides=(2, 2),
			padding="same"))

model.add(Convolution2D(filters = 64,
			kernel_size = (3,3),
			strides = 1,
			activation = "relu"))
'''
model.add(Convolution2D(filters = 64,
			kernel_size = (3,3),
			strides= 1,
			activation = "relu"))
'''
model.add(MaxPooling2D(pool_size=(2, 2),
			strides=(2, 2),
			padding="same"))

model.add(Dropout(0.2))

model.add(Flatten())

model.add(Dense(128,
		activation = "relu",
		kernel_initializer = "uniform"))

model.add(Dense(64,
		activation = "relu",
		kernel_initializer = "uniform"))

model.add(Dense(46,
		activation = "softmax",
		kernel_initializer = "uniform"))

model.compile(optimizer = "adam",
		loss = "categorical_crossentropy",
		metrics = ["accuracy"])

print model.summary()

model.fit_generator(
		trainGenerator,
		nb_epoch = 5,
		validation_data = validation_generator
		)

model.save("DevaModel.h5")