基于深度学习的身份证号码识别（OCR，Opencv，Pytorch）

前言

最近做了一个身份证号码识别项目，在此分享一下。视频效果如下所示，共有两种识别方法，其一就是直接上传身份证号码的截图进行识别，第二就是上传一张完整的身份证图像，然后通过逐步的处理定位身份证号码的位置，最后进行识别。视频效果如下所示：

身份证号码识别（Opencv，Pytorch）

模型结构

使用的深度学习模型为CRNN，模型代码如下所示：

# crnn.py
import argparse, os
import torch
import torch.nn as nn


class BidirectionalLSTM(nn.Module):

    def __init__(self, nInput_size, nHidden, nOut):
        super(BidirectionalLSTM, self).__init__()

        self.lstm = nn.LSTM(nInput_size, nHidden, bidirectional=True)
        self.linear = nn.Linear(nHidden * 2, nOut)

    def forward(self, input):
        recurrent, (hidden, cell) = self.lstm(input)
        T, b, h = recurrent.size()
        t_rec = recurrent.view(T * b, h)

        output = self.linear(t_rec)  # [T * b, nOut]
        output = output.view(T, b, -1)  # 输出变换为[seq,batch,类别总数]

        return output


class CNN(nn.Module):

    def __init__(self, imageHeight, nChannel):
        super(CNN, self).__init__()
        assert imageHeight % 32 == 0, 'image Height has to be a multiple of 32'

        self.depth_conv0 = nn.Conv2d(in_channels=nChannel, out_channels=nChannel, kernel_size=3, stride=1, padding=1,
                                     groups=nChannel)
        self.point_conv0 = nn.Conv2d(in_channels=nChannel, out_channels=64, kernel_size=1, stride=1, padding=0,
                                     groups=1)
        self.relu0 = nn.ReLU(inplace=True)
        self.pool0 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.depth_conv1 = nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1, groups=64)
        self.point_conv1 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=1, stride=1, padding=0, groups=1)
        self.relu1 = nn.ReLU(inplace=True)
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)

        self.depth_conv2 = nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1, groups=128)
        self.point_conv2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=1, stride=1, padding=0, groups=1)
        self.batchNorm2 = nn.BatchNorm2d(256)
        self.relu2 = nn.ReLU(inplace=True)

        self.depth_conv3 = nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1, groups=256)
        self.point_conv3 = nn.Conv2d(in_channels=256, out_channels=256, kernel_size=1, stride=1, padding=0, groups=1