【Tensorflow深度学习】实现手写字体识别、预测实战(附源码和数据集 超详细)

showswoller 2024-07-10 10:01:02 阅读 55

需要源码和数据集请点赞关注收藏后评论区留言私信~~~

一、数据集简介

下面用到的数据集基于IAM数据集的英文手写字体自动识别应用,IAM数据库主要包含手写的英文文本,可用于训练和测试手写文本识别以及执行作者的识别和验证,该数据库在ICDAR1999首次发布,并据此开发了基于隐马尔可夫模型的手写句子识别系统,并于ICPR2000发布,IAM包含不受约束的手写文本,以300dpi的分辨率扫描并保存为具有256级灰度的PNG图像,IAM手写数据库目前最新的版本为3.0,其主要结构如下

约700位作家贡献笔迹样本

超过1500页扫描文本

约6000个独立标记的句子

超过一万行独立标记的文本

超过十万个独立标记的空间

展示如下 有许多张手写照片 

 

 

二、实现步骤 

1:数据清洗

删除文件中备注说明以及错误结果,统计正确笔迹图形的数量,最后将整理后的数据进行随机无序化处理

2:样本分类

接下来对数据进行分类 按照8:1:1的比例将样本数据集分为三类数据集,分别是训练数据集 验证数据集和测试数据集,针对训练数据集进行训练可以获得模型,而测试数据集主要用于测试模型的有效性

3:实现字符和数字映射

利用Tensorflow库的Keras包的StringLookup函数实现从字符到数字的映射 主要参数说明如下

max_tokens:单词大小的最大值

num_oov_indices:out of vocabulary的大小

mask_token:表示屏蔽输入的大小

oov_token:仅当invert为True时使用 OOV索引的返回值 默认为UNK

4:进行卷积变化 

通过Conv2D函数实现二维卷积变换 主要参数说明如下

filters:整数值 代表输出空间的维度

kernel_size:一个整数或元组列表 指定卷积窗口的高度和宽度

strides:一个整数或元组列表 指定卷积沿高度和宽度的步幅

padding:输出图像的填充方式

activation:激活函数

三、效果展示 

读取部分手写样本的真实文本信息如下

训练结束后 得到训练模型 导入测试手写文本数据 进行手写笔迹预测 部分结果如下

 

四、结果总结 

观察预测结果可知,基于均值池化以及训练过程预警极值,大部分的英文字符能够得到准确的预测判定,训练的精度持续得到改善,损失值控制在比较合理的区间内,没有发生预测准确度连续多次无法改进的场景,模型稳定性较好

五、代码

部分代码如下 需要全部代码请点赞关注收藏后评论区留言私信~~~

<code>

from tensorflow.keras.layers.experimental.preprocessing import StringLookup

from tensorflow import keras

import matplotlib.pyplot as plt

import tensorflow as tf

import numpy as np

import os

plt.rcParams['font.family'] = ['Microsoft YaHei']

np.random.seed(0)

tf.random.set_seed(0)

# ## 切分数据

# In[ ]:

corpus_read = open("data/words.txt", "r").readlines()

corpus = []

length_corpus=0

for word in corpus_read:

if lit(" ")[1] == "ok"):

corpus.append(word)

np.random.shuffle(corpus)

length_corpus=len(corpus)

print(length_corpus)

corpus[400:405]

# 划分数据,按照 80:10:10 比例分配给训练:有效:测试 数据

# In[ ]:

train_flag = int(0.8 * len(corpus))

test_flag = int(0.9 * len(corpus))

train_data = corpus[:train_flag]

validation_data = corpus[train_flag:test_flag]

test_data = corpus[test_flag:]

train_data_len=len(train_data)

validation_data_len=len(validation_data)

test_data_len=len(test_data)

print("训练样本大小:", train_data_len)

print("验证样本大小:", validation_data_len)

print("测试样本大小:",test_data_len )

# In[ ]:

image_direct = "data\images"

def retrieve_image_info(data):

image_location = []

sample = []

for (i, corpus_row) in enumerate(data):

corpus_strip = corpus_row.strip()

corpus_strip = corpus_strip.split(" ")

image_name = corpus_strip[0]

leve1 = image_name.split("-")[0]

leve2 = image_name.split("-")[1]

image_location_detail = os.path.join(

image_direct, leve1, leve1 + "-" + leve2, image_name + ".png"

)

if os.path.getsize(image_location_detail) >0 :

image_location.append(image_location_detail)

sample.append(corpus_row.split("\n")[0])

print("手写图像路径:",image_location[0],"手写文本信息:",sample[0])

return image_location, sample

train_image, train_tag = retrieve_image_info(train_data)

validation_image, validation_tag = retrieve_image_info(validation_data)

test_image, test_tag = retrieve_image_info(test_data)

# In[ ]:

# 查找训练数据词汇最大长度

train_tag_extract = []

vocab = set()

max_len = 0

for tag in train_tag:

tag = tag.split(" ")[-1].strip()

for i in tag:

vocab.add(i)

max_len = max(max_len, len(tag))

train_tag_extract.append(tag)

print("最大长度: ", max_len)

print("单词大小: ", len(vocab))

print("单词内容: ", vocab)

train_tag_extract[40:45]

# In[ ]:

print(train_tag[50:54])

print(validation_tag[10:14])

print(test_tag[80:84])

def extract_tag_info(tags):

extract_tag = []

for tag in tags:

tag = tag.split(" ")[-1].strip()

extract_tag.append(tag)

return extract_tag

train_tag_tune = extract_tag_info(train_tag)

validation_tag_tune = extract_tag_info(validation_tag)

test_tag_tune = extract_tag_info(test_tag)

print(train_tag_tune[50:54])

print(validation_tag_tune[10:14])

print(test_tag_tune[80:84])

# In[ ]:

AUTOTUNE = tf.data.AUTOTUNE

# 映射单词到数字

string_to_no = StringLookup(vocabulary=list(vocab), invert=False)

# 映射数字到单词

no_map_string = StringLookup(

vocabulary=string_to_no.get_vocabulary(), invert=True)

# In[ ]:

def distortion_free_resize(image, img_size):

w, h = img_size

image = tf.image.resize(image, size=(h, w), preserve_aspect_ratio=True, antialias=False, name=None)

# 计算填充区域大小

pad_height = h - tf.shape(image)[0]

pad_width = w - tf.shape(image)[1]

if pad_height % 2 != 0:

height = pad_height // 2

pad_height_top = height + 1

pad_height_bottom = height

else:

pad_height_top = pad_height_bottom = pad_height // 2

if pad_width % 2 != 0:

width = pad_width // 2

pad_width_left = width + 1

pad_width_right = width

else:

pad_width_left = pad_width_right = pad_width // 2

image = tf.pad(

image,

paddings=[

[pad_height_top, pad_height_bottom],

[pad_width_left, pad_width_right],

[0, 0],

],

)

image = tf.transpose(image, perm=[1, 0, 2])

image = tf.image.flip_left_right(image)

return image

# In[ ]:

batch_size = 64

padding_token = 99

image_width = 128

image_height = 32

def preprocess_image(image_path, img_size=(image_width, image_height)):

image = tf.io.read_file(image_path)

image = tf.image.decode_png(image, 1)

image = distortion_free_resize(image, img_size)

image = tf.cast(image, tf.float32) / 255.0

return image

def vectorize_tag(tag):

tag = string_to_no(tf.strings.unicode_split(tag, input_encoding="UTF-8"))code>

length = tf.shape(tag)[0]

pad_amount = max_len - length

tag = tf.pad(tag, paddings=[[0, pad_amount]], constant_values=padding_token)

return tag

def process_images_tags(image_path, tag):

image = preprocess_image(image_path)

tag = vectorize_tag(tag)

return {"image": image, "tag": tag}

def prepare_dataset(image_paths, tags):

dataset = tf.data.Dataset.from_tensor_slices((image_paths, tags)).map(

process_images_tags, num_parallel_calls=AUTOTUNE

)

return dataset.batch(batch_size).cache().prefetch(AUTOTUNE)

# In[ ]:

train_final = prepare_dataset(train_image, train_tag_extract )

validation_final = prepare_dataset(validation_image, validation_tag_tune )

test_final = prepare_dataset(test_image, test_tag_tune )

print(train_final.take(1))

print(train_final)

# In[ ]:

plt.rcParams['font.family'] = ['Microsoft YaHei']

for data in train_final.take(1):

images, tags = data["image"], data["tag"]

_, ax = plt.subplots(4, 4, figsize=(15, 8))

for i in range(16):

img = images[i]

img = tf.image.flip_left_right(img)

img = tf.transpose(img, perm=[1, 0, 2])

img = (img * 255.0).numpy().clip(0, 255).astype(np.uint8)

img = img[:, :, 0]

tag = tags[i]

indices = tf.gather(tag, tf.where(tf.math.not_equal(tag, padding_token)))

tag = tf.strings.reduce_join(no_map_string(indices))

tag = tag.numpy().decode("utf-8")

ax[i // 4, i % 4].imshow(img)

ax[i // 4, i % 4].set_title(u"真实文本:%s"%tag)

ax[i // 4, i % 4].axis("on")

plt.show()

# In[ ]:

class CTCLoss(keras.layers.Layer):

def call(self, y_true, y_pred):

batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")code>

input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")code>

tag_length = tf.cast(tf.shape(y_true)[1], dtype="int64")code>

input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")code>

tag_length = tag_length * tf.ones(shape=(batch_len, 1), dtype="int64")code>

loss = keras.backend.ctc_batch_cost(y_true, y_pred, input_length, tag_length)

self.add_loss(loss)

return loss

def generate_model():

# Inputs to the model

input_img = keras.Input(shape=(image_width, image_height, 1), name="image")code>

tags = keras.layers.Input(name="tag", shape=(None,))code>

# First conv block.

t = keras.layers.Conv2D(

filters=32,

kernel_size=(3, 3),

activation="relu",code>

kernel_initializer="he_normal",code>

padding="same",code>

name="ConvolutionLayer1")(input_img)code>

t = keras.layers.AveragePooling2D((2, 2), name="AveragePooling_one")(t)code>

# Second conv block.

t = keras.layers.Conv2D(

filters=64,

kernel_size=(3, 3),

activation="relu",code>

kernel_initializer="he_normal",code>

padding="same",code>

name="ConvolutionLayer2")(t)code>

t = keras.layers.AveragePooling2D((2, 2), name="AveragePooling_two")(t)code>

#re_shape = (t,[(image_width // 4), -1])

#tf.dtypes.cast(t, tf.int32)

re_shape = ((image_width // 4), (image_height // 4) * 64)

t = keras.layers.Reshape(target_shape=re_shape, name="reshape")(t)code>

t = keras.layers.Dense(64, activation="relu", name="denseone",use_bias=False,code>

kernel_initializer='glorot_uniform',code>

bias_initializer='zeros')(t)code>

t = keras.layers.Dropout(0.4)(t)

# RNNs.

t = keras.layers.Bidirectional(

keras.layers.LSTM(128, return_sequences=True, dropout=0.4)

)(t)

t = keras.layers.Bidirectional(

keras.layers.LSTM(64, return_sequences=True, dropout=0.4)

)(t)

t = keras.layers.Dense(

len(string_to_no.get_vocabulary())+2, activation="softmax", name="densetwo"code>

)(t)

# Add CTC layer for calculating CTC loss at each step.

output = CTCLoss(name="ctc_loss")(tags, t)code>

# Define the model.

model = keras.models.Model(

inputs=[input_img, tags], outputs=output, name="handwriting"code>

)

# Optimizer.

# Compile the model and return.

model.compile(optimizer=keras.optimizers.Adam())

return model

# Get the model.

model = generate_model()

model.summary()

# In[ ]:

validation_images = []

validation_tags = []

for batch in validation_final:

validation_images.append(batch["image"])

validation_tags.append(batch["tag"])

# In[ ]:

#epochs = 20

model = generate_model()

prediction_model = keras.models.Model(

model.get_layer(name="image").input, model.get_layer(name="densetwo").output)code>

#edit_distance_callback = EarlyStoppingAtLoss()

epochs = 60

early_stopping_patience = 10

# Add early stopping

early_stopping = keras.callbacks.EarlyStopping(

monitor="val_loss", patience=early_stopping_patience, restore_best_weights=Truecode>

)

# Train the model.

history = model.fit(

train_final,

validation_data=validation_final,

epochs=60,callbacks=[early_stopping]

)

# ## Inference

# In[ ]:

plt.rcParams['font.family'] = ['Microsoft YaHei']

# A utility function to decode the output of the network.

def handwriting_prediction(pred):

input_len = np.ones(pred.shape[0]) * pred.shape[1]

= []

for j in results:

j = tf.gather(j, tf.where(tf.math.not_equal(j, -1)))

j = tf.strings.reduce_join(no_map_string(j)).numpy().decode("utf-8")

output_text.append(j)

return output_text

# Let's check results on some test samples.

for test in test_final.take(1):

test_images = test["image"]

_, ax = plt.subplots(4, 4, figsize=(15, 8))

predit = prediction_model.predict(test_images)

predit_text = handwriting_prediction(predit)

for k in range(16):

img = test_images[k]

img = tf.image.flip_left_right(img)

img = tf.transpose(img, perm=[1, 0, 2])

img = (img * 255.0).numpy().clip(0, 255).astype(np.uint8)

img = img[:, :, 0]

title = f"预测结果: {predit_text[k]}"

# In[ ]:

创作不易 觉得有帮助请点赞关注收藏~~~



声明

本文内容仅代表作者观点,或转载于其他网站,本站不以此文作为商业用途
如有涉及侵权,请联系本站进行删除
转载本站原创文章,请注明来源及作者。