基于深度学习和opencv的车牌识别系统

基于 https://github.com/duanshengliu/End-to-end-for-chinese-plate-recognition

原作者的现有系统进行二次开发

建议向原作者项目star

原作者 https://github.com/duanshengliu/End-to-end-for-chinese-plate-recognition

本次再开发利用tkinter重写编写界面

同时利用对图片每一帧图像加入视频分析模块

图片分析模块可以依据界面按钮提示进行相应功能

视频分析模块可以根据按钮提示进行对视频的分析 （视频模块的视频追踪处理时间较长，直至提示框弹出才会播放视频，建议等待些许时间）

只需运行git项目到本地，运行GUI.py即可

选择两个模块进入新的界面，根据按钮进行操作

本项目主要使用了CNN卷积神经网络+unet分割网络实现车牌识别。其中

CNN算法实现代码：

from tensorflow.keras import layers, losses, models
import numpy as np
import cv2
import os


'''
def cnn_train():
    char_dict = {"京": 0, "沪": 1, "津": 2, "渝": 3, "冀": 4, "晋": 5, "蒙": 6, "辽": 7, "吉": 8, "黑": 9, "苏": 10,
                 "浙": 11, "皖": 12, "闽": 13, "赣": 14, "鲁": 15, "豫": 16, "鄂": 17, "湘": 18, "粤": 19, "桂": 20,
                 "琼": 21, "川": 22, "贵": 23, "云": 24, "藏": 25, "陕": 26, "甘": 27, "青": 28, "宁": 29, "新": 30,
                 "0": 31, "1": 32, "2": 33, "3": 34, "4": 35, "5": 36, "6": 37, "7": 38, "8": 39, "9": 40,
                 "A": 41, "B": 42, "C": 43, "D": 44, "E": 45, "F": 46, "G": 47, "H": 48, "J": 49, "K": 50,
                 "L": 51, "M": 52, "N": 53, "P": 54, "Q": 55, "R": 56, "S": 57, "T": 58, "U": 59, "V": 60,
                 "W": 61, "X": 62, "Y": 63, "Z": 64}


    path = 'home/cnn_datasets/'
    pic_name = sorted(os.listdir(path))
    n = len(pic_name)
    X_train, y_train = [], []
    for i in range(n):
        print("正在读取第%d张图片" % i)
        img = cv2.imdecode(np.fromfile(path + pic_name[i], dtype=np.uint8), -1)
        label = [char_dict[name] for name in pic_name[i][0:7]]
        X_train.append(img)
        y_train.append(label)
    X_train = np.array(X_train)
    y_train = [np.array(y_train)[:, i] for i in range(7)]


    Input = layers.Input((80, 240, 3))
    x = Input
    x = layers.Conv2D(filters=16, kernel_size=(3, 3), strides=1, padding='same', activation='relu')(x)
    x = layers.MaxPool2D(pool_size=(2, 2), padding='same', strides=2)(x)
    for i in range(3):
        x = layers.Conv2D(filters=32 * 2 ** i, kernel_size=(3, 3), padding='valid', activation='relu')(x)
        x = layers.Conv2D(filters=32 * 2 ** i, kernel_size=(3, 3), padding='valid', activation='relu')(x)
        x = layers.MaxPool2D(pool_size=(2, 2), padding='same', strides=2)(x)
        x = layers.Dropout(0.5)(x)
    x = layers.Flatten()(x)
    x = layers.Dropout(0.3)(x)
    Output = [layers.Dense(65, activation='softmax', name='c%d' % (i + 1))(x) for i in range(7)]
    model = models.Model(inputs=Input, outputs=Output)
    model.summary()
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])


    print("开始训练cnn")
    model.fit(X_train, y_train, epochs=35)  # 总loss为7个loss的和
    model.save('cnn.h5')
    print('cnn.h5保存成功!!!')
'''

def cnn_predict(cnn, Lic_img):
    characters = ["京", "沪", "津", "渝", "冀", "晋", "蒙", "辽", "吉", "黑", "苏", "浙", "皖", "闽", "赣", "鲁", "豫",
                  "鄂", "湘", "粤", "桂", "琼", "川", "贵", "云", "藏", "陕", "甘", "青", "宁", "新", "0", "1", "2",
                  "3", "4", "5", "6", "7", "8", "9", "A", "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M",
                  "N", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z"]
    Lic_pred = []
    for lic in Lic_img:
        lic_pred = cnn.predict(lic.reshape(1, 80, 240, 3))
        lic_pred = np.array(lic_pred).reshape(7, 65)
        if len(lic_pred[lic_pred >= 0.8]) >= 4:
            chars = ''
            for arg in np.argmax(lic_pred, axis=1):  # 取每行中概率值最大的arg,将其转为字符
                chars += characters[arg]
            chars = chars[0:2] + '·' + chars[2:]
            Lic_pred.append((lic, chars))  # 将车牌和识别结果一并存入Lic_pred
    return Lic_pred

unet算法实现代码：

import numpy as np
import os
import cv2
from tensorflow.keras import layers, losses, models

'''
def unet_train():
    height = 512
    width = 512
    path = ''
    input_name = os.listdir(path + 'train_image')
    n = len(input_name)
    print(n)
    X_train, y_train = [], []
    for i in range(n):
        print("正在读取第%d张图片" % i)
        img = cv2.imread(path + 'train_image/%d.png' % i)
        label = cv2.imread(path + 'train_label/%d.png' % i)
        X_train.append(img)
        y_train.append(label)
    X_train = np.array(X_train)
    y_train = np.array(y_train)


    def Conv2d_BN(x, nb_filter, kernel_size, strides=(1, 1), padding='same'):
        x = layers.Conv2D(nb_filter, kernel_size, strides=strides, padding=padding)(x)
        x = layers.BatchNormalization(axis=3)(x)
        x = layers.LeakyReLU(alpha=0.1)(x)
        return x

    def Conv2dT_BN(x, filters, kernel_size, strides=(2, 2), padding='same'):
        x = layers.Conv2DTranspose(filters, kernel_size, strides=strides, padding=padding)(x)
        x = layers.BatchNormalization(axis=3)(x)
        x = layers.LeakyReLU(alpha=0.1)(x)
        return x

    inpt = layers.Input(shape=(height, width, 3))
    conv1 = Conv2d_BN(inpt, 8, (3, 3))
    conv1 = Conv2d_BN(conv1, 8, (3, 3))
    pool1 = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(conv1)

    conv2 = Conv2d_BN(pool1, 16, (3, 3))
    conv2 = Conv2d_BN(conv2, 16, (3, 3))
    pool2 = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(conv2)

    conv3 = Conv2d_BN(pool2, 32, (3, 3))
    conv3 = Conv2d_BN(conv3, 32, (3, 3))
    pool3 = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(conv3)

    conv4 = Conv2d_BN(pool3, 64, (3, 3))
    conv4 = Conv2d_BN(conv4, 64, (3, 3))
    pool4 = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(conv4)

    conv5 = Conv2d_BN(pool4, 128, (3, 3))
    conv5 = layers.Dropout(0.5)(conv5)
    conv5 = Conv2d_BN(conv5, 128, (3, 3))
    conv5 = layers.Dropout(0.5)(conv5)

    convt1 = Conv2dT_BN(conv5, 64, (3, 3))
    concat1 = layers.concatenate([conv4, convt1], axis=3)
    concat1 = layers.Dropout(0.5)(concat1)
    conv6 = Conv2d_BN(concat1, 64, (3, 3))
    conv6 = Conv2d_BN(conv6, 64, (3, 3))

    convt2 = Conv2dT_BN(conv6, 32, (3, 3))
    concat2 = layers.concatenate([conv3, convt2], axis=3)
    concat2 = layers.Dropout(0.5)(concat2)
    conv7 = Conv2d_BN(concat2, 32, (3, 3))
    conv7 = Conv2d_BN(conv7, 32, (3, 3))

    convt3 = Conv2dT_BN(conv7, 16, (3, 3))
    concat3 = layers.concatenate([conv2, convt3], axis=3)
    concat3 = layers.Dropout(0.5)(concat3)
    conv8 = Conv2d_BN(concat3, 16, (3, 3))
    conv8 = Conv2d_BN(conv8, 16, (3, 3))

    convt4 = Conv2dT_BN(conv8, 8, (3, 3))
    concat4 = layers.concatenate([conv1, convt4], axis=3)
    concat4 = layers.Dropout(0.5)(concat4)
    conv9 = Conv2d_BN(concat4, 8, (3, 3))
    conv9 = Conv2d_BN(conv9, 8, (3, 3))
    conv9 = layers.Dropout(0.5)(conv9)
    outpt = layers.Conv2D(filters=3, kernel_size=(1, 1), strides=(1, 1), padding='same', activation='relu')(conv9)

    model = models.Model(inpt, outpt)
    model.compile(optimizer='adam',
                  loss='mean_squared_error',
                  metrics=['accuracy'])
    model.summary()

    print("开始训练u-net")
    model.fit(X_train, y_train, epochs=100, batch_size=15)
    model.save('unet.h5')
    print('unet.h5保存成功!!!')
'''

def unet_predict(unet, img_src_path):
    img_src = cv2.imdecode(np.fromfile(img_src_path, dtype=np.uint8), -1)
    # img_src=cv2.imread(img_src_path)
    if img_src.shape != (512, 512, 3):
        img_src = cv2.resize(img_src, dsize=(512, 512), interpolation=cv2.INTER_AREA)[:, :, :3]  # dsize=(宽度,高度),[:,:,:3]是防止图片为4通道图片，后续无法reshape
    img_src = img_src.reshape(1, 512, 512, 3)

    img_mask = unet.predict(img_src)  # 归一化除以255后进行预测
    img_src = img_src.reshape(512, 512, 3)  # 将原图reshape为3维
    img_mask = img_mask.reshape(512, 512, 3)  # 将预测后图片reshape为3维
    img_mask = img_mask / np.max(img_mask) * 255  # 归一化后乘以255
    img_mask[:, :, 2] = img_mask[:, :, 1] = img_mask[:, :, 0]  # 三个通道保持相同
    img_mask = img_mask.astype(np.uint8)  # 将img_mask类型转为int型

    return img_src, img_mask

完整源码下载地址：https://download.csdn.net/download/FL1768317420/89325303