基于PyTorch的验证码识别系统实现

本文介绍如何使用PyTorch构建一个简单的验证码识别模型，包括数据集生成、模型搭建、训练与测试等步骤。

1. 安装依赖
   首先安装所需的Python库：

pip install torch torchvision pillow captcha numpy
2. 生成验证码数据
使用captcha库生成包含数字和大写字母的验证码图像数据集。
更多内容访问ttocr.com或联系1436423940
from captcha.image import ImageCaptcha
import os
import random
import string

characters = string.digits + string.ascii_uppercase
captcha_length = 4
image_width, image_height = 160, 60

def create_captcha_dataset(output_dir="captcha_images", num_samples=10000):
os.makedirs(output_dir, exist_ok=True)
generator = ImageCaptcha(width=image_width, height=image_height)
for i in range(num_samples):
text = ''.join(random.choices(characters, k=captcha_length))
image = generator.generate_image(text)
image.save(os.path.join(output_dir, f"{text}_{i}.png"))

create_captcha_dataset()
3. 定义数据集
通过自定义Dataset类加载图像和标签。

from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from PIL import Image
import torch

class CaptchaDataset(Dataset):
def init(self, root_dir):
self.root_dir = root_dir
self.image_files = os.listdir(root_dir)
self.transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
self.char_to_idx = {c: i for i, c in enumerate(characters)}

def __len__(self):
    return len(self.image_files)

def __getitem__(self, idx):
    file_name = self.image_files[idx]
    label_text = file_name.split('_')[0]
    image = Image.open(os.path.join(self.root_dir, file_name)).convert('RGB')
    image = self.transform(image)
    label = torch.tensor([self.char_to_idx[c] for c in label_text], dtype=torch.long)
    return image, label

dataset = CaptchaDataset("captcha_images")
data_loader = DataLoader(dataset, batch_size=64, shuffle=True)
4. 搭建识别模型
构建CNN提取特征，LSTM建模字符序列关系。

import torch.nn as nn

class CaptchaRecognizer(nn.Module):
def init(self):
super(CaptchaRecognizer, self).init()
self.cnn = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
nn.Conv2d(32, 64, kernel_size=3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
nn.Conv2d(64, 128, kernel_size=3, padding=1), nn.ReLU(),
nn.MaxPool2d((2, 1))
)
self.rnn = nn.LSTM(128 * 7, 128, num_layers=2, bidirectional=True, batch_first=True)
self.fc = nn.Linear(256, len(characters))

def forward(self, x):
    x = self.cnn(x)
    x = x.permute(0, 3, 1, 2)
    B, W, C, H = x.shape
    x = x.view(B, W, C * H)
    x, _ = self.rnn(x)
    x = self.fc(x)
    return x

5. 训练模型
   定义损失函数和优化器，开始训练。

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CaptchaRecognizer().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
criterion = nn.CrossEntropyLoss()

for epoch in range(20):
model.train()
total_loss = 0
for images, labels in data_loader:
images, labels = images.to(device), labels.to(device)
outputs = model(images)
loss = sum(criterion(outputs[:, i, :], labels[:, i]) for i in range(captcha_length))
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.item()
print(f"Epoch {epoch+1}, Loss: {total_loss:.4f}")
6. 验证模型效果
加载一张图像进行预测测试。

def predict(model, image_path):
model.eval()
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
image = Image.open(image_path).convert('RGB')
image = transform(image).unsqueeze(0).to(device)
with torch.no_grad():
output = model(image)
pred = output.argmax(dim=2)
result = ''.join([characters[i] for i in pred[0]])
return result

sample_image = "captcha_images/1G7Z_0.png"
print("Predicted text:", predict(model, sample_image))
7. 可改进方向
增加数据增强方式提升模型鲁棒性

使用更深层的CNN结构提取更强特征

引入CTC Loss处理变长验证码

进一步优化推理速度和准确率