文章目录
一、前期工作
- 导入库
- 图片生成函数
- 导入数据
- 生成数据集函数
二、CNN模型建立
三、训练模型函数
四、训练模型与结果
五、验证
大家好，我是微学AI，今天给大家带来一个利用卷积神经网络（CNN）进行中文OCR识别，实现自己的一个OCR识别工具。
一个OCR识别系统，其目的很简单，只是要把影像作一个转换，使影像内的图形继续保存、有表格则表格内资料及影像内的文字，一律变成计算机文字，使能达到影像资料的储存量减少、识别出的文字可再使用及分析，这样可节省人力打字的时间。
中文OCR识别的注意流程图：
一、前期工作
1.导入库
import numpy as np
from PIL import Image, ImageDraw, ImageFont
import cv2
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from tensorflow.keras.optimizers import SGD
from tensorflow.keras.utils import plot_model
import matplotlib.pyplot as plt
#导入字体
DroidSansFallbackFull = ImageFont.truetype("DroidSansFallback.ttf", 36, 0)
fonts = [DroidSansFallbackFull,]
2.数据集生成函数
#生成图片，48*48大小
def affineTrans(image, mode, size=(48, 48)):
# print("AffineTrans ...")
if mode == 0: # padding移动
which = np.array([0, 0, 0, 0])
which[np.random.randint(0, 4)] = np.random.randint(0, 10)
which[np.random.randint(0, 4)] = np.random.randint(0, 10)
image = cv2.copyMakeBorder(image, which[0], which[0], which[0], which[0], cv2.BORDER_CONSTANT, value=0)
image = cv2.resize(image, size)
if mode == 1:
scale = np.random.randint(48, int(48 * 1.4))
center = [scale / 2, scale / 2]
image = cv2.resize(image, (scale, scale))
image = image[int(center[0] - 24):int(center[0] + 24), int(center[1] - 24):int(center[1] + 24)]
return image
#图片处理 除噪
def noise(image, mode=1):
# print("Noise ...")
noise_image = (image.astype(float) / 255) + (np.random.random((48, 48)) * (np.random.random() * 0.3))
norm = (noise_image - noise_image.min()) / (noise_image.max() - noise_image.min())
if mode == 1:
norm = (norm * 255).astype(np.uint8)
return norm
#绘制中文的图片
def DrawChinese(txt, font):
# print("DrawChinese...")
image = np.zeros(shape=(48, 48), dtype=np.uint8)
x = Image.fromarray(image)
draw = ImageDraw.Draw(x)
draw.text((8, 2), txt, (255), font=font)
result = np.array(x)
return result
#图片标准化
def norm(image):
# print("norm...")
return image.astype(np.float) / 255
3.导入数据
char_set = open("chinese.txt",encoding = "utf-8").readlines()[0]
print(len(char_set[0])) # 打印字的个数
4.生成数据集函数
# 生成数据：训练集和标签
def Genernate(batchSize, charset):
# print("Genernate...")
# pass
label = [];
training_data = [];
for x in range(batchSize):
char_id = np.random.randint(0, len(charset))
font_id = np.random.randint(0, len(fonts))
y = np.zeros(dtype=np.float, shape=(len(charset)))
image = DrawChinese(charset[char_id], fonts[font_id])
image = affineTrans(image, np.random.randint(0, 2))
# image = noise(image)
# image = augmentation(image,np.random.randint(0,8))
image = noise(image)
image_norm = norm(image)
image_norm = np.expand_dims(image_norm, 2)
training_data.append(image_norm)
y[char_id] = 1
label.append(y)
return np.array(training_data), np.array(label)
二、CNN模型建立
def Getmodel(nb_classes):
img_rows, img_cols = 48, 48
nb_filters = 32
nb_pool = 2
nb_conv = 4
model = Sequential()
print("sequential..")
model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
padding='same',
input_shape=(img_rows, img_cols, 1)))
print("add convolution2D...")
model.add(Activation('relu'))
print("activation ...")
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv,padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
return model
#评估模型
def eval(model, X, Y):
print("Eval ...")
res = model.predict(X)
三、训练模型函数
#训练函数
def Training(charset):
model = Getmodel(len(charset))
while (1):
X, Y = Genernate(64, charset)
model.train_on_batch(X, Y)
print(model.loss)
#训练生成模型
def TrainingGenerator(charset, test=1):
set = Genernate(64, char_set)
model = Getmodel(len(charset))
BatchSize = 64
model.fit_generator(generator=Genernator(charset, BatchSize), steps_per_epoch=BatchSize * 10, epochs=15,
validation_data=set)
model.save("ocr.h5")
X = set[0]
Y = set[1]
if test == 1:
print("============6 Test == 1 ")
for i, one in enumerate(X):
x = one
res = model.predict(np.array([x]))
classes_x = np.argmax(res, axis=1)[0]
print(classes_x)
print(u"Predict result：", char_set[classes_x], u"Real result：", char_set[Y[i].argmax()])
image = (x.squeeze() * 255).astype(np.uint8)
cv2.imwrite("{0:05d}.png".format(i), image)
四、训练模型与结果
TrainingGenerator(char_set) #函数TrainingGenerator 开始训练
Epoch 1/15
640/640 [==============================] - 63s 76ms/step - loss: 8.1078 - accuracy: 3.4180e-04 - val_loss: 8.0596 - val_accuracy: 0.0000e+00
Epoch 2/15
640/640 [==============================] - 102s 159ms/step - loss: 7.5234 - accuracy: 0.0062 - val_loss: 6.2163 - val_accuracy: 0.0781
Epoch 3/15
640/640 [==============================] - 38s 60ms/step - loss: 5.9793 - accuracy: 0.0425 - val_loss: 4.1687 - val_accuracy: 0.3281
Epoch 4/15
640/640 [==============================] - 45s 71ms/step - loss: 5.0450 - accuracy: 0.0889 - val_loss: 3.1590 - val_accuracy: 0.4844
Epoch 5/15
640/640 [==============================] - 37s 58ms/step - loss: 4.5251 - accuracy: 0.1292 - val_loss: 2.5326 - val_accuracy: 0.5938
Epoch 6/15
640/640 [==============================] - 38s 60ms/step - loss: 4.1708 - accuracy: 0.1687 - val_loss: 1.9666 - val_accuracy: 0.7031
Epoch 7/15
640/640 [==============================] - 35s 54ms/step - loss: 3.9068 - accuracy: 0.1951 - val_loss: 1.8039 - val_accuracy: 0.7812
...
910
Predict result： 妻 Real result： 妻
1835
Predict result： 莱 Real result： 莱
3107
Predict result： 阀 Real result： 阀
882
Predict result： 培 Real result： 培
1241
Predict result： 鼓 Real result： 鼓
735
Predict result： 豆 Real result： 豆
1844
Predict result： 巾 Real result： 巾
1714
Predict result： 跌 Real result： 跌
2580
Predict result： 骄 Real result： 骄
1788
Predict result： 氧 Real result： 氧
生成字体图片：
五、验证
model = tf.keras.models.load_model("ocr.h5")
img1 = cv2.imread('00001.png',0)
img = cv2.resize(img1,(48,48))
print(img.shape)
img2 = tf.expand_dims(img, 0)
res = model.predict(img2)
classes_x = np.argmax(res, axis=1)[0]
print(classes_x)
print(u"Predict result：", char_set[classes_x])
中文字：
预测结果为”莱；
数据集的获取私信我！后期有更深入的OCR识别功能呈现，敬请期待！
文章出处登录后可见！
已经登录？立即刷新
