基于深度学习和opencv的甲骨文识别系统_甲骨文机器学习识别

最近做了一个甲骨文识别项目，在此分享一下。

文末附有源码。
视频展示：

运行界面：

识别结果：

本文一共可识别1135个甲骨文，数据集已经放到下载链接中：
下面是代码部分：
读取数据：

import cv2 as cv
import os
import numpy as np


f=open('lab.txt',encoding='utf-8')
lines=f.readlines()
f.close()

split=0.2
np.random.seed(10)
np.random.shuffle(lines)
bb=int(len(lines)*(1-0.2))
vv=len(lines)-bb
train_lines=lines[:bb]
valid_lines=lines[bb:]

def generate(train=True,valid=False,batch_size=32):
    while True:
        ee=np.eye(1185)
        if train:
            linnns=train_lines
        elif valid:
            linnns=valid_lines
        else:break

        x=[]
        y=[]
        for lin in linnns:
            lu_jing=lin.split()[0]
            lab=lin.split()[1]
            src=cv.imdecode(np.fromfile(lu_jing, dtype=np.uint8), 1)
            h,w,d=src.shape[0],src.shape[1],src.shape[2]
            if h==96 and w==96 and d==3:
                src=(src/255).astype('float32')
                ll=ee[int(lab)]
                x.append(src)
                y.append(ll)
                if len(x)==batch_size:
                    x_train=np.array(x)
                    y_train=np.array(y)
                    x=[]
                    y=[]
                    yield x_train,y_train


if __name__ == '__main__':
    generate()

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

训练网络模型：

from tensorflow.keras.layers import Conv2D,MaxPooling2D,Input,Flatten,Dense,Dropout
from tensorflow.keras import Model
from tensorflow.keras.callbacks import (EarlyStopping, ReduceLROnPlateau,
                                        TensorBoard,ModelCheckpoint)
from get_data import generate,bb,vv


def mode(shape=(96,96,3)):
    inputs=Input(shape=shape)
    x=Conv2D(filters=6,kernel_size=5,strides=(1,1),padding='same',activation='relu')(inputs)
    x=MaxPooling2D(pool_size=(2,2),strides=(2,2),padding='same')(x)
    x=Conv2D(filters=16,kernel_size=3,strides=(1,1),padding='same',activation='relu')(x)
    x = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(x)
    x=Flatten()(x)
    x=Dense(1000,activation='relu')(x)
    x=Dropout(rate=0.5)(x)
    x=Dense(500,activation='relu')(x)
    y = Dense(1185, activation='softmax')(x)
    model=Model(inputs,y)
    return model

modell=mode()
modell.summary()
if __name__ == '__main__':
    modell.compile(
        loss='categorical_crossentropy',
        optimizer='adam',
        metrics=['accuracy']
    )

    log_dir = 'logs/'
    logging = TensorBoard(log_dir=log_dir)
    checkpoint = ModelCheckpoint(log_dir + 'ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5',
                                 monitor='val_loss', save_weights_only=True, save_best_only=False, period=1)
    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=3, verbose=1)
    early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=10, verbose=1)
    TensorBoard = TensorBoard(log_dir='./model', histogram_freq=1)

    batch_size=50
    hist = modell.fit_generator(generate(batch_size=batch_size),
                                steps_per_epoch=bb//batch_size,
                                validation_data=generate(valid=True,batch_size=batch_size),
                                validation_steps=vv//batch_size,
                                epochs=50,
                                callbacks=[logging, checkpoint, reduce_lr, early_stopping])


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

预测：

from model import modell
import cv2 as cv
import numpy as np
with open('answer.txt','r',encoding='utf-8') as f:
    lines=f.readlines()
modell.load_weights('logs/ep030-loss0.037-val_loss0.024.h5')
def ppre(src):
    #src=cv.imdecode(np.fromfile('ancient_3_exp/jia/丘/0/O000255_exp_1.png', dtype=np.uint8), 1)
    src=np.reshape(src,(1,src.shape[0],src.shape[1],src.shape[2]))
    src=(src/255).astype('float32')
    pre=modell.predict(src)[0]
    pre=np.argmax(pre)
    return lines[pre]

if __name__ == '__main__':
    src = cv.imdecode(np.fromfile('ancient_3_exp/jia/丘/0/O000255_exp_1.png', dtype=np.uint8), 1)
    zti=ppre(src)
    print(zti)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

界面已经使用pyqt5做好，下载以后只需运行main.py程序即可，下图是程序目录：
1

如有疑问可私信作者。
下载地址：下载列表13