Merge branch 'main' of https://bdgit.educoder.net/p2fq9vxcb/cxy_zhw_Imag_Enhanc_License_recog

.idea/.gitignore

@@ -0,0 +1,3 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml

.idea/Imag_Enhanc_License_recog-main.iml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,41 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="21">
+            <item index="0" class="java.lang.String" itemvalue="torchvision" />
+            <item index="1" class="java.lang.String" itemvalue="Flask" />
+            <item index="2" class="java.lang.String" itemvalue="tqdm" />
+            <item index="3" class="java.lang.String" itemvalue="protobuf" />
+            <item index="4" class="java.lang.String" itemvalue="tensorflow" />
+            <item index="5" class="java.lang.String" itemvalue="Flask-Cors" />
+            <item index="6" class="java.lang.String" itemvalue="faiss-cpu" />
+            <item index="7" class="java.lang.String" itemvalue="numpy" />
+            <item index="8" class="java.lang.String" itemvalue="requests" />
+            <item index="9" class="java.lang.String" itemvalue="opencv-python-headless" />
+            <item index="10" class="java.lang.String" itemvalue="Pillow" />
+            <item index="11" class="java.lang.String" itemvalue="tensorboard" />
+            <item index="12" class="java.lang.String" itemvalue="ipython" />
+            <item index="13" class="java.lang.String" itemvalue="albumentations" />
+            <item index="14" class="java.lang.String" itemvalue="scipy" />
+            <item index="15" class="java.lang.String" itemvalue="h5py" />
+            <item index="16" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="17" class="java.lang.String" itemvalue="opencv_contrib_python" />
+            <item index="18" class="java.lang.String" itemvalue="packaging" />
+            <item index="19" class="java.lang.String" itemvalue="terminaltables" />
+            <item index="20" class="java.lang.String" itemvalue="gradio" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="pandas" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Imag_Enhanc_License_recog-main.iml" filepath="$PROJECT_DIR$/.idea/Imag_Enhanc_License_recog-main.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

PlateDetect.py

@@ -0,0 +1,37 @@
+#coding:utf-8
+from ultralytics import YOLO
+import cv2
+
+# 所需加载的模型目录
+path = 'models/best.pt'
+# 需要检测的图片地址
+img_path = "TestFiles/aa.jpg"
+
+# 加载预训练模型
+model = YOLO(path, task='detect')
+
+# 检测图片
+results = model(img_path)
+
+# 读取原始图片
+img = cv2.imread(img_path)
+
+# 遍历所有检测结果
+for result in results:
+    # 获取检测框的坐标
+    for i, box in enumerate(result.boxes):
+        x1, y1, x2, y2 = map(int, box.xyxy[0])
+        # 裁剪检测框内的图像
+        cropped_img = img[y1:y2, x1:x2]
+        # 显示裁剪后的图像
+        cv2.imshow("Cropped Image", cropped_img)
+        cv2.waitKey(0)
+        # 构建保存路径
+        save_path = f"TestFiles/cropped_license_plate_{i}.jpg"
+        # 保存裁剪后的图像
+        cv2.imwrite(save_path, cropped_img)
+
+# 显示原始图像上的检测结果
+res = results[0].plot()
+cv2.imshow("YOLOv5 Detection", res)
+cv2.waitKey(0)

README.md

@@ -0,0 +1,35 @@
+## 1.创建虚拟环境并安装相关依赖
+
+#创建虚拟环境 
+
+conda create -n pytorch_1.8 python=3.8
+
+#进入虚拟环境
+
+conda activate pytorch_1.8
+
+#安装项目依赖包
+
+python -m pip install opencv-python -i https://pypi.tuna.tsinghua.edu.cn/simple/
+
+python -m pip install matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple/
+
+pip install gradio==3.47.1
+
+(缺少哪个包就类似方法安装哪个包即可)
+
+
+
+## 2.运行项目脚本
+
+#进入到项目虚拟环境
+
+conda activate pytorch_1.8
+
+#cd 到项目根目录
+
+cd Imag_Enhanc_License_recog-main/
+
+#运行项目
+
+python demo_ui_main.py

carPlate_recognize.py

@@ -0,0 +1,85 @@
+import cv2
+import numpy as np
+
+'''
+基于Opencv图像处理的车牌定位和分割
+'''
+def car_plate_recognize(car):
+    """=========================== 1. 定位车牌（车牌检测）==========================="""
+    # 蓝色、黄色和绿色所对应的色彩空间
+    lower_blue = np.array([100, 110, 110])
+    upper_blue = np.array([130, 255, 255])
+    lower_yellow = np.array([15, 55, 55])
+    upper_yellow = np.array([50, 255, 255])
+    lower_green = np.array([35, 100, 100])
+    upper_green = np.array([85, 255, 255])
+
+    hsv = cv2.cvtColor(car, cv2.COLOR_BGR2HSV)  # 将BGR图像转化到HSV的颜色空间
+    mask_blue = cv2.inRange(hsv, lower_blue, upper_blue)
+    mask_yellow = cv2.inRange(hsv, lower_yellow, upper_yellow)
+    mask_green = cv2.inRange(hsv, lower_green, upper_green)
+    mask_plate = cv2.bitwise_or(mask_blue, mask_yellow)
+    mask_plate = cv2.bitwise_or(mask_plate, mask_green)
+
+    # 根据阈值找到对应颜色
+    mask = cv2.cvtColor(mask_plate, cv2.COLOR_GRAY2BGR)
+    mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
+    Matrix = np.ones((20, 20), np.uint8)
+    mask1 = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, Matrix)
+    mask = cv2.morphologyEx(mask1, cv2.MORPH_OPEN, Matrix)  # 形态学开运算
+    ret, mask = cv2.threshold(mask, 0, 255, cv2.THRESH_BINARY)  # 二值化进而获取轮廓
+    contours, hierarchy = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)  # 获取轮廓 contours
+
+    # 初始化 box
+    box = None
+
+    # 寻找轮廓最大的 定位车牌
+    for i in range(len(contours)):
+        cnt = contours[i]
+        area = cv2.contourArea(cnt)
+        if area > 3000:
+            rect = cv2.minAreaRect(cnt)
+            box = cv2.boxPoints(rect)
+            box = np.int_(box)
+            break  # 找到一个符合条件的就跳出循环
+
+    if box is None:
+        raise ValueError("No contours found that meet the size requirement.")
+
+    plate = cv2.drawContours(car.copy(), [box], -1, (0, 255, 0), 3)
+
+    """=========================== 2. 分割车牌中的每个字符 ==========================="""
+    ys = [box[0, 1], box[1, 1], box[2, 1], box[3, 1]]
+    xs = [box[0, 0], box[1, 0], box[2, 0], box[3, 0]]
+    ys_sorted_index = np.argsort(ys)
+    xs_sorted_index = np.argsort(xs)
+    x1 = box[xs_sorted_index[0], 0]
+    x2 = box[xs_sorted_index[3], 0]
+    y1 = box[ys_sorted_index[0], 1]
+    y2 = box[ys_sorted_index[3], 1]
+    ROI_plate = plate[y1:y2, x1:x2]
+    ROI_plate_gray = cv2.cvtColor(ROI_plate, cv2.COLOR_BGR2GRAY)  # 灰度化
+    ROI_plate_blur = cv2.GaussianBlur(ROI_plate_gray, (5, 5), 0)  # 高斯滤波
+    ret, ROI_plate_Binary = cv2.threshold(ROI_plate_blur, 127, 255, cv2.THRESH_BINARY)  # 二值化
+    # 形态学腐蚀 去除边框
+    kernel = np.ones((5, 5), dtype=np.uint8)
+    ROI_erode = cv2.erode(ROI_plate_Binary, kernel, iterations=1)
+    # 根据宽度 裁剪7个字符
+    width = ROI_erode.shape[1]
+    height = ROI_erode.shape[0]
+    word_0 = ROI_erode[0:height, 0:np.uint8(height / 2)]
+    word_1 = ROI_erode[0:height, np.uint8(height / 2):height]
+    size = np.uint8((width - height) / 5)
+    word_2 = ROI_erode[0:height, height + 0 * size:height + 1 * size]
+    word_3 = ROI_erode[0:height, height + 1 * size:height + 2 * size]
+    word_4 = ROI_erode[0:height, height + 2 * size:height + 3 * size]
+    word_5 = ROI_erode[0:height, height + 3 * size:height + 4 * size]
+    word_6 = ROI_erode[0:height, height + 4 * size:height + 5 * size]
+    word_all = [word_0, word_1, word_2, word_3, word_4, word_5, word_6]
+    return plate, word_all
+
+
+if __name__ == "__main__":
+    car = cv2.imread(r'/mnt/data/cropped_license_plate_0.jpg', 1)
+    plate, _ = car_plate_recognize(car)
+    cv2.imwrite("plate.jpg", plate)

demo_ui_main.py

@@ -0,0 +1,15 @@
+import gradio as gr
+from tab1_1 import img_handle_1
+from tab1_2 import img_handle_2
+from tab1_3 import img_handle_3
+from tab2 import Car_segmentation
+from tab3 import Car_detection
+
+
+if __name__ == "__main__":
+    gr.close_all()
+    with gr.TabbedInterface(
+            [img_handle_1(), img_handle_2(), img_handle_3(), Car_segmentation(), Car_detection()],
+            ["图像处理1:几何处理", "图像处理2:颜色空间变化", "图像处理3:频率像素点操作", "进阶功能:车牌定位与分割", "YOLO车牌检测与OCR识别"],
+    ) as demo:
+        demo.launch(share=True)

detect_tools.py

@@ -0,0 +1,91 @@
+# encoding:utf-8
+import cv2
+from PyQt5.QtGui import QPixmap, QImage
+import numpy as np
+from PIL import Image,ImageDraw,ImageFont
+import csv
+import os
+
+# fontC = ImageFont.truetype("Font/platech.ttf", 20, 0)
+
+# 绘图展示
+def cv_show(name,img):
+	cv2.imshow(name, img)
+	cv2.waitKey(0)
+	cv2.destroyAllWindows()
+
+
+def drawRectBox(image, rect, addText, fontC, color=(0,0,255)):
+    """
+    绘制矩形框与结果
+    :param image: 原始图像
+    :param rect: 矩形框坐标, int类型
+    :param addText: 类别名称
+    :param fontC: 字体
+    :return:
+    """
+    # 绘制位置方框
+    cv2.rectangle(image, (rect[0], rect[1]),
+                 (rect[2], rect[3]),
+                 color, 2)
+
+    # 绘制字体背景框
+    # cv2.rectangle(image, (rect[0] - 1, rect[1] - 50), (rect[2], rect[1]), color, -1, cv2.LINE_AA)
+    # 图片 添加的文字 位置 字体 字体大小 字体颜色 字体粗细.无法正常显示中文
+    # cv2.putText(image, addText, (int(rect[0])+2, int(rect[1])-3), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 255), 2)
+
+    # 可以显示中文
+    # 字体自适应大小
+    font_size = int((rect[3]-rect[1])/1.5)
+    fontC = ImageFont.truetype("Font/platech.ttf", font_size, 0)
+    img = Image.fromarray(image)
+    draw = ImageDraw.Draw(img)
+    draw.text((rect[0]+2, rect[1]-font_size), addText, (0, 0, 255), font=fontC)
+    imagex = np.array(img)
+    return imagex
+
+
+def img_cvread(path):
+    # 读取含中文名的图片文件
+    # img = cv2.imread(path)
+    img = cv2.imdecode(np.fromfile(path, dtype=np.uint8), cv2.IMREAD_COLOR)
+    return img
+
+
+def draw_boxes(img, boxes):
+    for each in boxes:
+        x1 = each[0]
+        y1 = each[1]
+        x2 = each[2]
+        y2 = each[3]
+        cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), 2)
+    return img
+
+
+
+def cvimg_to_qpiximg(cvimg):
+    height, width, depth = cvimg.shape
+    cvimg = cv2.cvtColor(cvimg, cv2.COLOR_BGR2RGB)
+    qimg = QImage(cvimg.data, width, height, width * depth, QImage.Format_RGB888)
+    qpix_img = QPixmap(qimg)
+    return qpix_img
+
+
+
+
+# 封装函数:图片上显示中文
+def cv2AddChineseText(img, text, position, textColor=(0, 255, 0), textSize=50):
+    if (isinstance(img, np.ndarray)):  # 判断是否OpenCV图片类型
+        img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
+    # 创建一个可以在给定图像上绘图的对象
+    draw = ImageDraw.Draw(img)
+    # 字体的格式
+    fontStyle = ImageFont.truetype(
+        "simsun.ttc", textSize, encoding="utf-8")
+    # 绘制文本
+    draw.text(position, text, textColor, font=fontStyle)
+    # 转换回OpenCV格式
+    return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)
+
+
+

flagged/log.csv

@@ -0,0 +1,3 @@
+query_image,output,flag,username,timestamp
+flagged\query_image\84d31d63af14e21377a9\down.jpeg,flagged\output\c822449a03f2e35edc0f\image.webp,,,2024-07-02 03:56:38.879751
+flagged\query_image\1b33b1e3b74157eda3d3\013671875-90_268-248480_423559-419546_248559_250482_423480-0_0_3_24_25_32_28_30-153-86.jpg,,,,2024-07-02 04:01:23.109896

imgTest.py

@@ -0,0 +1,71 @@
+#coding:utf-8
+from ultralytics import YOLO
+import cv2
+import detect_tools as tools
+from PIL import ImageFont
+from paddleocr import PaddleOCR
+import os
+os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"#程序中链接了多个 OpenMP 运行时库的副本
+
+def get_license_result(ocr,image):
+    """
+    image:输入的车牌截取照片
+    输出，车牌号与置信度
+    """
+    result = ocr.ocr(image, cls=True)[0]
+    if result:
+        license_name, conf = result[0][1]
+        if '·' in license_name:
+            license_name = license_name.replace('·', '')
+        return license_name, conf
+    else:
+        return None, None
+
+# 需要检测的图片地址
+img_path = "TestFiles/down.jpeg"
+now_img = tools.img_cvread(img_path)
+
+fontC = ImageFont.truetype("Font/platech.ttf", 50, 0)
+# 加载ocr模型
+cls_model_dir = 'paddleModels/whl/cls/ch_ppocr_mobile_v2.0_cls_infer'
+rec_model_dir = 'paddleModels/whl/rec/ch/ch_PP-OCRv4_rec_infer'
+ocr = PaddleOCR(use_angle_cls=False, lang="ch", det=False, cls_model_dir=cls_model_dir,rec_model_dir=rec_model_dir)
+
+# 所需加载的模型目录
+path = 'models/best.pt'
+# 加载预训练模型
+# conf	0.25	object confidence threshold for detection
+# iou	0.7	int.ersection over union (IoU) threshold for NMS
+model = YOLO(path, task='detect')
+# model = YOLO(path, task='detect',conf=0.5)
+# 检测图片
+results = model(img_path)[0]
+
+location_list = results.boxes.xyxy.tolist()
+if len(location_list) >= 1:
+    location_list = [list(map(int, e)) for e in location_list]
+    # 截取每个车牌区域的照片
+    license_imgs = []
+    for each in location_list:
+        x1, y1, x2, y2 = each
+        cropImg = now_img[y1:y2, x1:x2]
+        license_imgs.append(cropImg)
+        # cv2.imshow('111',cropImg)  # cv2.waitKey(0)
+    # 车牌识别结果
+    lisence_res = []
+    conf_list = []
+    for each in license_imgs:
+        license_num, conf = get_license_result(ocr, each)
+        print(license_num, conf)
+        if license_num:
+            lisence_res.append(license_num)
+            conf_list.append(conf)
+        else:
+            lisence_res.append('无法识别')
+            conf_list.append(0)
+    for text, box in zip(lisence_res, location_list):
+        now_img = tools.drawRectBox(now_img, box, text, fontC)
+
+# now_img = cv2.resize(now_img,dsize=None,fx=0.5,fy=0.5,interpolation=cv2.INTER_LINEAR)
+# cv2.imshow("YOLOv8 Detection", now_img)
+# cv2.waitKey(0)

img_enhancement.py

@@ -0,0 +1,218 @@
+import cv2
+import numpy as np
+import albumentations as A
+
+#图像处理类
+class Image_enhancement:
+    def __init__(self,):
+        pass
+    """===============================1.几何处理:=================================="""
+    # 1.1 图片旋转(可选择旋转角度)
+    def roate(self, frame=None,angle=30):
+        h, w = frame.shape[:2]
+        M = cv2.getRotationMatrix2D((w / 2, h / 2), angle, 1)
+        img_roate = cv2.warpAffine(frame, M, (w, h))
+        return img_roate
+
+    # 1.2 图片缩放(可选择缩放大小)
+    def resize(self, frame=None,w=224,h=224):
+        img_resized = cv2.resize(frame, (w, h))  # w,h
+        return img_resized
+    
+    """===============================2.颜色空间变化:=================================="""
+    # 2.1 图片的对比度、饱和度、亮度、色调变化
+    def ColorJitter(self, frame=None,brightness=0,hue=0,saturation=0,contrast=0):
+        transform = A.ColorJitter(brightness=float(brightness),hue=float(hue),saturation=float(saturation),contrast=float(contrast),p=1)
+        img_result = transform(image=np.array(frame))
+        img_color = img_result['image']
+        return img_color
+
+    # 2.2 灰度图转换
+    def ToGray(self, frame=None ):
+        # cvtColor的第一个参数是处理的图像，第二个是RGB2GRAY
+        gray_img = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        return gray_img
+
+    # 2.3 直方图均衡化
+    def equalhist(self, frame=None):
+        # 直方图均衡化增强对比度:通过调整图像的灰度分布，增加图像的对比度，从而使图像更加清晰。
+        frame_lab = cv2.cvtColor(frame, cv2.COLOR_BGR2LAB)
+        frame_lab[:, :, 0] = cv2.equalizeHist(frame_lab[:, :, 0])
+        enhanced_frame = cv2.cvtColor(frame_lab, cv2.COLOR_LAB2BGR)
+        return enhanced_frame
+
+    """===============================3.频率像素点操作:=================================="""
+    # 3.1 模糊
+    # 3.1.1 高斯滤波
+    def Gaussblur(self, frame=None,count=3):
+        transform = A.GaussianBlur(blur_limit=count, p=1)
+        img_result = transform(image=np.array(frame))['image']
+        return img_result
+
+    # 3.1.3 随机模糊
+    def Blur(self, frame=None, count=3):
+        transform = A.Blur(blur_limit=count, p=1)
+        img_result = transform(image=np.array(frame))['image']
+        return img_result
+
+    # 3.1.2 中值滤波
+    def Medianblur(self, frame=None, count=3):
+        transform = A.MedianBlur(blur_limit=count, p=1)
+        img_result = transform(image=np.array(frame))['image']
+        return img_result
+
+    # 3.2 锐化
+    # 3.2.1 使用sobel算子进行锐化
+    def sobel(self, frame=None):
+        img_gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        kernelx1 = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]], dtype=int)
+        kernely1 = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype=int)
+        x1 = cv2.filter2D(img_gray, cv2.CV_16S, kernelx1)
+        y1 = cv2.filter2D(img_gray, cv2.CV_16S, kernely1)
+        absX1 = cv2.convertScaleAbs(x1)
+        absY1 = cv2.convertScaleAbs(y1)
+        img_result = cv2.addWeighted(absX1, 0.5, absY1, 0.5, 0)
+        return img_result
+
+    # 3.2.2 使用Prewitt算子进行锐化
+    def Prewitt(self, frame=None):
+        img_gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        kernelx1 = np.array([[-1, 0, 1], [-1, 0, 1], [-1, 0, 1]], dtype=int)
+        kernely1 = np.array([[-1, -1, 1], [0, 0, 0], [1, 1, 1]], dtype=int)
+        x1 = cv2.filter2D(img_gray, cv2.CV_16S, kernelx1)
+        y1 = cv2.filter2D(img_gray, cv2.CV_16S, kernely1)
+        absX1 = cv2.convertScaleAbs(x1)
+        absY1 = cv2.convertScaleAbs(y1)
+        img_result = cv2.addWeighted(absX1, 0.5, absY1, 0.5, 0)
+        return img_result
+
+    # 3.2.3 使用robert算子进行锐化
+    def robert(self, frame=None):
+        img_gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        kernelx1 = np.array([[-1, 0], [0, 1]], dtype=int)
+        kernely1 = np.array([[0, -1], [1, 0]], dtype=int)
+        x1 = cv2.filter2D(img_gray, cv2.CV_16S, kernelx1)
+        y1 = cv2.filter2D(img_gray, cv2.CV_16S, kernely1)
+        absX1 = cv2.convertScaleAbs(x1)
+        absY1 = cv2.convertScaleAbs(y1)
+        img_result = cv2.addWeighted(absX1, 0.5, absY1, 0.5, 0)
+        return img_result
+
+    # 3.3 添加噪声
+    # 3.3.1 添加高斯噪声
+    def add_gaussian_noise(self, frame=None, mean=0,sigma=30):
+        # 生成高斯噪声矩阵
+        row, col, ch = frame.shape
+        gaussian = np.random.randn(row, col, ch) * sigma + mean
+        gaussian = gaussian.reshape(row, col, ch)
+        img_result = frame + gaussian
+        # 转换数据类型为8位无符号整数类型
+        img_result = cv2.convertScaleAbs(img_result)
+        return img_result
+    # 3.3.2 添加椒盐噪声
+    def add_salt_and_pepper_noise(self, frame=None, percentage=0):  # percentage [0,100]
+        # 确保百分比在 0 到 100 之间
+        if percentage < 0 or percentage > 100:
+            percentage=0
+
+        # 生成椒盐噪声矩阵
+        row, col, ch = frame.shape
+        noise = np.zeros((row, col, ch), np.uint8)
+        for i in range(row):
+            for j in range(col):
+                rand = np.random.randint(0, 100)
+                if rand < percentage:
+                    noise[i][j] = [0, 0, 0]
+                elif rand > 100 - percentage:
+                    noise[i][j] = [255, 255, 255]
+                else:
+                    noise[i][j] = frame[i][j]
+
+        # 将椒盐噪声矩阵添加到原始图像中
+        img_result = cv2.add(frame, noise)
+        return img_result
+    # 3.3.3 添加均值噪声
+    def add_mean_noise(self, frame=None, mean=0,std_dev=30):
+        # 生成均值噪声矩阵
+        row, col, ch = frame.shape
+        noise = np.random.normal(mean, std_dev, (row, col, ch)).astype(np.uint8)
+        # 将均值噪声矩阵添加到原始图像中
+        img_result = cv2.add(frame, noise)
+        return img_result
+
+    # 3.4 边缘检测
+    def Canny(self, frame=None):
+        # 转为灰度图
+        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+        # 高斯滤波
+        gray = cv2.GaussianBlur(gray, (5, 5), 0)
+        # 边缘检测
+        canny_edged = cv2.Canny(gray, 30, 250)
+        return canny_edged
+
+
+if __name__ == "__main__":
+    # 类实例化
+    img_enhance = Image_enhancement()
+
+    img_path = r'images/car_test.jpg'
+    img = cv2.imread(img_path)
+
+    # 测试1.1 图片旋转(可选择旋转角度)
+    img_roate = img_enhance.roate(img,45)
+    cv2.imwrite("out_imgs/out_1.jpg",img_roate)
+    # 测试1.2 图片缩放(可选择缩放大小)
+    img_resized = img_enhance.resize(img, w=224, h=224)
+    cv2.imwrite("out_imgs/out_2.jpg", img_resized)
+
+    # 测试2.1 图片的对比度、饱和度、亮度、色调变化
+    img_resized = img_enhance.ColorJitter(img, brightness=10,hue=10,saturation=10,contrast=10)
+    cv2.imwrite("out_imgs/out_3.jpg", img_resized)
+    # 测试2.2 灰度图转化
+    gray_img = img_enhance.ToGray(img)
+    cv2.imwrite("out_imgs/out_4.jpg", gray_img)
+    # 测试2.3 直方图均衡化
+    enhanced_frame = img_enhance.equalhist(img)
+    cv2.imwrite("out_imgs/out_5.jpg", enhanced_frame)
+
+    # 3.1 模糊
+    # 3.1.1 高斯滤波
+    img_gauss = img_enhance.Gaussblur(img,count=5)
+    cv2.imwrite("out_imgs/out_6.jpg", img_gauss)
+
+    # 3.1.2 随机模糊
+    img_Blur = img_enhance.Blur(img, count=5)
+    cv2.imwrite("out_imgs/out_7.jpg", img_Blur)
+
+    # 3.1.3 中值滤波
+    img_Medianblur = img_enhance.Medianblur(img, count=5)
+    cv2.imwrite("out_imgs/out_8.jpg", img_Medianblur)
+
+    # 3.2 锐化
+    # 3.2.1 使用sobel算子进行锐化
+    img_sobel = img_enhance.sobel(img)
+    cv2.imwrite("out_imgs/out_9.jpg", img_sobel)
+    # 3.2.2 使用Prewitt算子进行锐化
+    img_Prewitt = img_enhance.Prewitt(img)
+    cv2.imwrite("out_imgs/out_10.jpg", img_Prewitt)
+    # 3.2.3 使用robert算子进行锐化
+    img_robert = img_enhance.robert(img)
+    cv2.imwrite("out_imgs/out_11.jpg", img_robert)
+
+    # 3.3 添加噪声
+    # 3.3.1 添加高斯噪声
+    img_gaussian_noise = img_enhance.add_gaussian_noise(img,mean=0,sigma=30)
+    cv2.imwrite("out_imgs/out_12.jpg", img_gaussian_noise)
+    # 3.3.2 添加椒盐噪声
+    img_salt_and_pepper_noise = img_enhance.add_salt_and_pepper_noise(img, percentage=10)
+    cv2.imwrite("out_imgs/out_13.jpg", img_salt_and_pepper_noise)
+    # 3.3.3 添加均值噪声
+    img_mean_noise = img_enhance.add_mean_noise(img, mean=0, std_dev=30)
+    cv2.imwrite("out_imgs/out_14.jpg", img_mean_noise)
+
+    # 3.4 边缘检测
+    img_Canny = img_enhance.Canny(img)
+    cv2.imwrite("out_imgs/out_15.jpg", img_Canny)
+
+
+

tab1_1.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from img_enhancement import Image_enhancement
+
+"""1.1 对图像进行几何处理:图片旋转、图片缩放"""
+
+# 类实例化
+img_enhance = Image_enhancement()
+
+def img_handle_1():
+    def pridict_1(query_image=None,angle=30):
+        img_roate = img_enhance.roate(query_image, angle)
+        return img_roate
+
+    def pridict_2(query_image=None,w=224,h=224):
+        img_resized = img_enhance.resize(query_image, int(w), int(h))
+        return img_resized
+
+    title = "<h1 align='center'>图像处理操作1:几何处理</h1>"
+    description = "1.对图像进行几何处理:图片旋转、图片缩放"     # "频率像素点操作:模糊、锐化、添加噪声、边缘检测等操作"
+
+    with gr.Blocks() as demo:
+        gr.Markdown(title)
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column(scale=1):
+                img = gr.components.Image(label="图片")
+                angle_num = gr.components.Slider(minimum=0, maximum=360, step=5, value=45, label="选择要旋转的角度")
+                btn_1 = gr.Button("图片旋转", )
+
+                w = gr.Number(label="图片缩放宽为：",value=224)
+                h = gr.Number(label="图片缩放高为：", value=224)
+                btn_2 = gr.Button("图片缩放", )
+
+            with gr.Column(scale=1):
+                out = gr.components.Image(label="处理后的图片为", height="auto")
+
+        btn_1.click(fn=pridict_1, inputs=[img, angle_num], outputs=out)
+
+        btn_2.click(fn=pridict_2, inputs=[img, w,h], outputs=out)
+
+    return demo
+
+
+if __name__ == "__main__":
+    with gr.TabbedInterface(
+            [img_handle_1()],
+            ["图像处理1:几何处理"],
+    ) as demo:
+        demo.launch()

tab1_2.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from img_enhancement import Image_enhancement
+
+"""1.2 对图像进行颜色空间变化:图片的对比度调整、灰度图转换、直方图均衡化"""
+
+# 类实例化
+img_enhance = Image_enhancement()
+
+def img_handle_2():
+    def pridict_1(query_image=None,brightness=10,hue=10,contrast=10,saturation=10):
+        img_Color = img_enhance.ColorJitter(query_image, brightness,hue,saturation,contrast)
+        return img_Color
+
+    def pridict_2(query_image=None,method="灰度化"):
+        if method=="灰度化":
+            img_out = img_enhance.ToGray(query_image)
+        elif method=="直方图均衡化":
+            img_out = img_enhance.equalhist(query_image)
+        return img_out
+
+    title = "<h1 align='center'>图像处理操作2:颜色空间变化</h1>"
+    description = "2.对图像进行颜色空间变化:图片的对比度调整、灰度图转换、直方图均衡化"     # "颜色空间变化:图片的对比度调整、灰度图转换、直方图均衡化；" "频率像素点操作:模糊、锐化、添加噪声、边缘检测等操作"
+
+    with gr.Blocks() as demo:
+        gr.Markdown(title)
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column(scale=1):
+                img = gr.components.Image(label="图片")
+                brightness = gr.components.Slider(minimum=0, maximum=100, step=5, value=10, label="选择亮度")
+                hue = gr.components.Slider(minimum=0, maximum=100, step=5, value=10, label="选择色调")
+                contrast = gr.components.Slider(minimum=0, maximum=100, step=5, value=10, label="选择对比度")
+                saturation = gr.components.Slider(minimum=0, maximum=100, step=5, value=10, label="选择饱和度")
+                btn_1 = gr.Button("对比度调整", )
+
+                method = gr.components.Radio(label="算法选择", choices=["灰度化", "直方图均衡化"],
+                                            value="灰度化",)
+                btn_2 = gr.Button("点击转化", )
+
+            with gr.Column(scale=1):
+                out = gr.components.Image(label="处理后的图片为", height="auto")
+
+        btn_1.click(fn=pridict_1, inputs=[img, brightness,hue,contrast,saturation], outputs=out)
+
+        btn_2.click(fn=pridict_2, inputs=[img, method], outputs=out)
+
+    return demo
+
+
+if __name__ == "__main__":
+    with gr.TabbedInterface(
+            [img_handle_2()],
+            ["图像处理2:颜色空间变化"],
+    ) as demo:
+        demo.launch()

tab1_3.py

@@ -0,0 +1,91 @@
+import gradio as gr
+from img_enhancement import Image_enhancement
+
+"""1.3 对图像进行频率像素点操作:模糊、锐化、添加噪声、边缘检测等操作"""
+
+# 类实例化
+img_enhance = Image_enhancement()
+
+def img_handle_3():
+    def pridict_1(query_image=None,method_1="高斯滤波",count=3):
+        if method_1 == "高斯滤波":
+            img_mohu = img_enhance.Gaussblur(query_image,count)
+        elif method_1 == "随机模糊":
+            img_mohu = img_enhance.Blur(query_image, count)
+        else: # 中值滤波
+            img_mohu = img_enhance.Medianblur(query_image, count=5)
+        return img_mohu
+
+    def pridict_2(query_image=None,method_2="robert"):
+        if method_2=="sobel":
+            img_out = img_enhance.sobel(query_image)
+        elif method_2=="Prewitt":
+            img_out = img_enhance.Prewitt(query_image)
+        else:#robert
+            img_out = img_enhance.robert(query_image)
+        return img_out
+
+    def pridict_3(query_image=None,method_3="高斯噪声",mean=0,sigma=30,percentage=10):
+        if method_3=="高斯噪声":
+            img_noise = img_enhance.add_gaussian_noise(query_image,mean,sigma)
+        elif method_3=="椒盐噪声":
+            img_noise = img_enhance.add_salt_and_pepper_noise(query_image, percentage)
+        else:# 均值噪声
+            img_noise = img_enhance.add_mean_noise(query_image, mean, sigma)
+        return img_noise
+
+    def pridict_4(query_image=None,method_4="yes"):
+        if method_4=="yes":
+            img_detect= img_enhance.Canny(query_image)
+        else: #no
+            img_detect = query_image
+        return img_detect
+
+    title = "<h1 align='center'>图像处理操作3:频率像素点操作</h1>"
+    description = "3.对图像进行频率像素点操作:模糊、锐化、添加噪声、边缘检测等操作"
+
+    with gr.Blocks() as demo:
+        gr.Markdown(title)
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column(scale=1):
+                img = gr.components.Image(label="图片")
+                method_1 = gr.components.Radio(label="模糊算法选择", choices=["高斯滤波", "随机模糊","中值滤波"],
+                                             value="高斯滤波", )
+                count = gr.components.Slider(minimum=0, maximum=8, step=1, value=3, label="模糊次数")
+
+                btn_1 = gr.Button("模糊处理", )
+
+                method_2 = gr.components.Radio(label="算子选择", choices=["sobel", "Prewitt","robert"],
+                                            value="robert",)
+                btn_2 = gr.Button("锐化处理", )
+
+                method_3 = gr.components.Radio(label="添加噪声类型选择", choices=["高斯噪声", "椒盐噪声", "均值噪声"],
+                                               value="高斯噪声", )
+                mean = gr.components.Slider(minimum=0, maximum=100, step=2, value=0, label="均值")
+                sigma = gr.components.Slider(minimum=0, maximum=100, step=2, value=30, label="标准差")
+                percentage = gr.components.Slider(minimum=0, maximum=100, step=5, value=30, label="百分比")
+                btn_3 = gr.Button("添加噪声", )
+
+                method_4 = gr.components.Radio(label="是否边缘检测", choices=["yes","no"],
+                                               value="yes", )
+                btn_4 = gr.Button("边缘检测", )
+
+
+            with gr.Column(scale=1):
+                out = gr.components.Image(label="处理后的图片为", height="auto")
+
+        btn_1.click(fn=pridict_1, inputs=[img, method_1,count], outputs=out)
+        btn_2.click(fn=pridict_2, inputs=[img, method_2], outputs=out)
+        btn_3.click(fn=pridict_3, inputs=[img, method_3,mean,sigma,percentage], outputs=out)
+        btn_4.click(fn=pridict_4, inputs=[img,method_4], outputs=out)
+
+    return demo
+
+
+if __name__ == "__main__":
+    with gr.TabbedInterface(
+            [img_handle_3()],
+            ["图像处理3:频率像素点操作"],
+    ) as demo:
+        demo.launch()

tab2.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import cv2
+from carPlate_recognize import car_plate_recognize
+
+def Car_segmentation():
+    def pridict(query_image=None):
+        img_cvt = cv2.cvtColor(query_image, cv2.COLOR_BGR2RGB)
+        plate, word_all = car_plate_recognize(img_cvt)
+        return plate,word_all
+
+    title = "<h1 align='center'>基于Opencv图像处理的车牌定位和分割</h1>"
+    description = "对输入的车牌进行车牌的定位与分割操作"
+    examples = [['images/car.jpg'],['images/car.png'],['images/car_test.jpg']]
+    
+    with gr.Blocks() as demo:
+        gr.Markdown(title)
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column(scale=1):
+                #with gr.Column(scale=2):
+                img = gr.components.Image(label="图片")
+                btn = gr.Button("点击定位与分割", )
+            with gr.Column(scale=1):
+                out_1 = gr.components.Image(label="车牌定位:",height="auto")
+                out_2 = gr.Gallery(label="车牌分割:",columns=[4], height="auto",object_fit="contain")
+
+        inputs = [img]
+        outputs = [out_1,out_2]
+        btn.click(fn=pridict, inputs=inputs, outputs=outputs)
+        gr.Examples(examples, inputs=inputs)
+        
+    return demo
+        
+    
+if __name__ == "__main__":
+    with gr.TabbedInterface(
+            [Car_segmentation()],
+            ["Opencv车牌定位与分割"],
+    ) as demo:
+        demo.launch(show_api=False,inbrowser=False,)#auth=("admin", '1234')

tab3.py

@@ -0,0 +1,84 @@
+import gradio as gr
+import cv2
+import time
+from ultralytics import YOLO
+from paddleocr import PaddleOCR
+import numpy as np
+import detect_tools as tools
+from imgTest import get_license_result
+import os
+
+os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
+
+# 加载YOLOv8检测模型
+model_path = 'models/best.pt'
+yolo_model = YOLO(model_path, task='detect')
+
+# 加载车牌识别模型
+cls_model_dir = 'paddleModels/whl/cls/ch_ppocr_mobile_v2.0_cls_infer'
+rec_model_dir = 'paddleModels/whl/rec/ch/ch_PP-OCRv4_rec_infer'
+ocr = PaddleOCR(use_angle_cls=False, lang="ch", det=False, cls_model_dir=cls_model_dir, rec_model_dir=rec_model_dir)
+
+
+def Car_detection():
+    def predict_image(query_image):
+        start_time = time.time()
+
+        # 图像预处理
+        img = cv2.cvtColor(query_image, cv2.COLOR_BGR2RGB)
+        print(f"Image preprocessing time: {time.time() - start_time:.2f}s")
+
+        # 使用YOLOv8检测车辆和车牌位置
+        yolo_start = time.time()
+        results = yolo_model(img)[0]
+        yolo_output = img.copy()  # 复制原图像用于显示YOLO结果
+        location_list = results.boxes.xyxy.tolist()
+        print(f"YOLO detection time: {time.time() - yolo_start:.2f}s")
+
+        # 处理每个检测到的车牌区域
+        license_numbers = []
+        for location in location_list:
+            x1, y1, x2, y2 = list(map(int, location))
+            crop_img = img[y1:y2, x1:x2]
+
+            # 使用PaddleOCR识别车牌号
+            license_num, confidence = get_license_result(ocr, crop_img)
+            if license_num:
+                license_numbers.append(license_num)
+            else:
+                license_numbers.append("无法识别")
+
+            # 在YOLO结果图上绘制检测框
+            cv2.rectangle(yolo_output, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        return yolo_output, "\n".join(license_numbers)
+
+    title = "<h1 align='center'>基于Opencv图像处理的车牌检测与识别</h1>"
+    description = "上传一张包含车辆的图像，系统将检测车辆并识别车牌号码"
+    # examples = [['images/car.jpg'], ['images/car.png'], ['images/car_test.jpg']]
+
+    with gr.Blocks() as demo:
+        gr.Markdown(title)
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column(scale=1):
+                img = gr.components.Image(label="上传图片")
+                btn = gr.Button("点击检测与识别")
+            with gr.Column(scale=1):
+                out_1 = gr.components.Image(label="YOLO定位结果:", height="auto")
+                out_2 = gr.components.Textbox(label="车牌识别结果:", type="text", lines=6)
+
+        inputs = [img]
+        outputs = [out_1, out_2]
+        btn.click(fn=predict_image, inputs=inputs, outputs=outputs)
+        # gr.Examples(examples, inputs=inputs)
+
+    return demo
+
+
+if __name__ == "__main__":
+    with gr.TabbedInterface(
+            [Car_detection()],
+            ["Opencv车牌检测与识别"],
+    ) as demo:
+        demo.launch(show_api=False, inbrowser=True)