test

.gitignore

@@ -153,4 +153,6 @@ cython_debug/
 
 # dataset
 实验七/cache/
-实验七/models/
+实验七/models/
+实验八/cache/
+实验八/models/

requirements.txt

@@ -1,5 +1,6 @@
 tqdm
 opencv-contrib-python
+opencv-python
 numpy
 pandas
 matplotlib
@@ -10,4 +11,5 @@ jupyterlab-language-pack-zh-CN
 icecream
 torch
 torchvision
-rich
+rich
+dlib

test/2024,12,03/main.py

@@ -0,0 +1,20 @@
+import cv2 as cv
+import dlib
+def draw_rect(img, faces):
+    for face in faces:
+        cv.rectangle(img,(face.left(),face.top()),(face.right(),face.bottom()),(0,255,0),2)
+    return img
+
+if __name__ == '__main__':
+    cap = cv.VideoCapture(0)
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+        frame_gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
+        detector = dlib.get_frontal_face_detector()
+        result = detector(frame_gray,1)
+        img_reslut = draw_rect(frame.copy(),result)
+        cv.imshow("frame",img_reslut)
+        cv.waitKey(1)
+    cap.release()

大作业/14.1/14.1.py

@@ -0,0 +1,255 @@
+# -*- coding: utf-8 -*-
+ 
+import cv2
+import numpy as np
+
+
+def stretch(img):
+    '''
+    图像拉伸函数
+    '''
+    maxi=float(img.max())
+    mini=float(img.min())
+    
+    for i in range(img.shape[0]):
+        for j in range(img.shape[1]):
+            img[i,j]=(255/(maxi-mini)*img[i,j]-(255*mini)/(maxi-mini))
+    
+    return img
+
+def dobinaryzation(img):
+    '''
+    二值化处理函数
+    '''
+    maxi=float(img.max())
+    mini=float(img.min())
+    
+    x=maxi-((maxi-mini)/2)
+    #二值化,返回阈值ret  和  二值化操作后的图像thresh
+    ret,thresh=cv2.threshold(img,x,255,cv2.THRESH_BINARY)
+    #返回二值化后的黑白图像
+    return thresh
+
+def find_rectangle(contour):
+    '''
+    寻找矩形轮廓
+    '''
+    y,x=[],[]
+    
+    for p in contour:
+        y.append(p[0][0])
+        x.append(p[0][1])
+    
+    return [min(y),min(x),max(y),max(x)]
+
+def locate_license(img,afterimg):
+    '''
+    定位车牌号
+    '''
+    contours,hierarchy=cv2.findContours(img,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
+    
+    #找出最大的三个区域
+    block=[]
+    for c in contours:
+        #找出轮廓的左上点和右下点，由此计算它的面积和长度比
+        r=find_rectangle(c)
+        a=(r[2]-r[0])*(r[3]-r[1])   #面积
+        s=(r[2]-r[0])*(r[3]-r[1])   #长度比
+        
+        block.append([r,a,s])
+    #选出面积最大的3个区域
+    block=sorted(block,key=lambda b: b[1])[-3:]
+    
+    #使用颜色识别判断找出最像车牌的区域
+    maxweight,maxindex=0,-1
+    for i in range(len(block)):
+        b=afterimg[block[i][0][1]:block[i][0][3],block[i][0][0]:block[i][0][2]]
+        #BGR转HSV
+        hsv=cv2.cvtColor(b,cv2.COLOR_BGR2HSV)
+        #蓝色车牌的范围
+        lower=np.array([100,50,50])
+        upper=np.array([140,255,255])
+        #根据阈值构建掩膜
+        mask=cv2.inRange(hsv,lower,upper)
+        #统计权值
+        w1=0
+        for m in mask:
+            w1+=m/255
+        
+        w2=0
+        for n in w1:
+            w2+=n
+            
+        #选出最大权值的区域
+        if w2>maxweight:
+            maxindex=i
+            maxweight=w2
+            
+    return block[maxindex][0]
+
+def find_license(img):
+    '''
+    预处理函数
+    '''
+    m=400*img.shape[0]/img.shape[1]
+    
+    #压缩图像
+    img=cv2.resize(img,(400,int(m)),interpolation=cv2.INTER_CUBIC)
+    
+    #BGR转换为灰度图像
+    gray_img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
+    
+    #灰度拉伸
+    stretchedimg=stretch(gray_img)
+    
+    '''进行开运算，用来去除噪声'''
+    r=16
+    h=w=r*2+1
+    kernel=np.zeros((h,w),np.uint8)
+    cv2.circle(kernel,(r,r),r,1,-1)
+    #开运算
+    openingimg=cv2.morphologyEx(stretchedimg,cv2.MORPH_OPEN,kernel)
+    #获取差分图，两幅图像做差  cv2.absdiff('图像1','图像2')
+    strtimg=cv2.absdiff(stretchedimg,openingimg)
+    
+    #图像二值化
+    binaryimg=dobinaryzation(strtimg)
+    
+    #canny边缘检测
+    canny=cv2.Canny(binaryimg,binaryimg.shape[0],binaryimg.shape[1])
+    
+    '''消除小的区域，保留大块的区域，从而定位车牌'''
+    #进行闭运算
+    kernel=np.ones((5,19),np.uint8)
+    closingimg=cv2.morphologyEx(canny,cv2.MORPH_CLOSE,kernel)
+    
+    #进行开运算
+    openingimg=cv2.morphologyEx(closingimg,cv2.MORPH_OPEN,kernel)
+    
+    #再次进行开运算
+    kernel=np.ones((11,5),np.uint8)
+    openingimg=cv2.morphologyEx(openingimg,cv2.MORPH_OPEN,kernel)
+    
+    #消除小区域，定位车牌位置
+    rect=locate_license(openingimg,img)
+    
+    return rect,img
+
+def cut_license(afterimg,rect):
+    '''
+    图像分割函数
+    '''
+    #转换为宽度和高度
+    rect[2]=rect[2]-rect[0]
+    rect[3]=rect[3]-rect[1]
+    rect_copy=tuple(rect.copy())
+    rect=[0,0,0,0]
+    #创建掩膜
+    mask=np.zeros(afterimg.shape[:2],np.uint8)
+    #创建背景模型  大小只能为13*5，行数只能为1，单通道浮点型
+    bgdModel=np.zeros((1,65),np.float64)
+    #创建前景模型
+    fgdModel=np.zeros((1,65),np.float64)
+    #分割图像
+    cv2.grabCut(afterimg,mask,rect_copy,bgdModel,fgdModel,5,cv2.GC_INIT_WITH_RECT)
+    mask2=np.where((mask==2)|(mask==0),0,1).astype('uint8')
+    img_show=afterimg*mask2[:,:,np.newaxis]
+    
+    return img_show
+
+def deal_license(licenseimg):
+    '''
+    车牌图片二值化
+    '''
+    #车牌变为灰度图像
+    gray_img=cv2.cvtColor(licenseimg,cv2.COLOR_BGR2GRAY)
+    
+    #均值滤波  去除噪声
+    kernel=np.ones((3,3),np.float32)/9
+    gray_img=cv2.filter2D(gray_img,-1,kernel)
+    
+    #二值化处理
+    ret,thresh=cv2.threshold(gray_img,120,255,cv2.THRESH_BINARY)
+    
+    return thresh
+
+
+def find_end(start,arg,black,white,width,black_max,white_max):
+    end=start+1
+    for m in range(start+1,width-1):
+        if (black[m] if arg else white[m])>(0.98*black_max if arg else 0.98*white_max):
+            end=m
+            break
+    return end
+                
+
+if __name__=='__main__':
+    img=cv2.imread('car.jpg',cv2.IMREAD_COLOR)
+    #预处理图像
+    rect,afterimg=find_license(img)
+    
+    #框出车牌号
+    cv2.rectangle(afterimg,(rect[0],rect[1]),(rect[2],rect[3]),(0,255,0),2)
+    cv2.imshow('afterimg',afterimg)
+    
+    #分割车牌与背景
+    cutimg=cut_license(afterimg,rect)
+    cv2.imshow('cutimg',cutimg)
+    
+    #二值化生成黑白图
+    thresh=deal_license(cutimg)
+    cv2.imshow('thresh',thresh)
+    cv2.imwrite("cp.jpg",thresh)
+    cv2.waitKey(0)
+    
+    #分割字符
+    '''
+    判断底色和字色
+    '''
+    #记录黑白像素总和
+    white=[]
+    black=[]
+    height=thresh.shape[0]  #263
+    width=thresh.shape[1]   #400
+    #print('height',height)
+    #print('width',width)
+    white_max=0
+    black_max=0
+    #计算每一列的黑白像素总和
+    for i in range(width):
+        line_white=0
+        line_black=0
+        for j in range(height):
+            if thresh[j][i]==255:
+                line_white+=1
+            if thresh[j][i]==0:
+                line_black+=1
+        white_max=max(white_max,line_white)
+        black_max=max(black_max,line_black)
+        white.append(line_white)
+        black.append(line_black)
+        print('white',white)
+        print('black',black)
+    #arg为true表示黑底白字，False为白底黑字
+    arg=True
+    if black_max<white_max:
+        arg=False
+    
+    n=1
+    start=1
+    end=2
+    while n<width-2:
+        n+=1
+        #判断是白底黑字还是黑底白字  0.05参数对应上面的0.95 可作调整
+        if(white[n] if arg else black[n])>(0.02*white_max if arg else 0.02*black_max):
+            start=n
+            end=find_end(start,arg,black,white,width,black_max,white_max)
+            n=end
+            if end-start>5:
+                cj=thresh[1:height,start:end]
+                cv2.imshow('cutlicense',cj)
+                cv2.waitKey(0)
+    
+    
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()

大作业/14.1/labelmap_det.txt

@@ -0,0 +1,402 @@
+label: 0
+display_name: "background"
+label: 1
+display_name: "accordion"
+label: 2
+display_name: "airplane"
+label: 3
+display_name: "ant"
+label: 4
+display_name: "antelope"
+label: 5
+display_name: "apple"
+label: 6
+display_name: "armadillo"
+label: 7
+display_name: "artichoke"
+label: 8
+display_name: "axe"
+label: 9
+display_name: "baby_bed"
+label: 10
+display_name: "backpack"
+label: 11
+display_name: "bagel"
+label: 12
+display_name: "balance_beam"
+label: 13
+display_name: "banana"
+label: 14
+display_name: "band_aid"
+label: 15
+display_name: "banjo"
+label: 16
+display_name: "baseball"
+label: 17
+display_name: "basketball"
+label: 18
+display_name: "bathing_cap"
+label: 19
+display_name: "beaker"
+label: 20
+display_name: "bear"
+label: 21
+display_name: "bee"
+label: 22
+display_name: "bell_pepper"
+label: 23
+display_name: "bench"
+label: 24
+display_name: "bicycle"
+label: 25
+display_name: "binder"
+label: 26
+display_name: "bird"
+label: 27
+display_name: "bookshelf"
+label: 28
+display_name: "bow_tie"
+label: 29
+display_name: "bow"
+label: 30
+display_name: "bowl"
+label: 31
+display_name: "brassiere"
+label: 32
+display_name: "burrito"
+label: 33
+display_name: "bus"
+label: 34
+display_name: "butterfly"
+label: 35
+display_name: "camel"
+label: 36
+display_name: "can_opener"
+label: 37
+display_name: "car"
+label: 38
+display_name: "cart"
+label: 39
+display_name: "cattle"
+label: 40
+display_name: "cello"
+label: 41
+display_name: "centipede"
+label: 42
+display_name: "chain_saw"
+label: 43
+display_name: "chair"
+label: 44
+display_name: "chime"
+label: 45
+display_name: "cocktail_shaker"
+label: 46
+display_name: "coffee_maker"
+label: 47
+display_name: "computer_keyboard"
+label: 48
+display_name: "computer_mouse"
+label: 49
+display_name: "corkscrew"
+label: 50
+display_name: "cream"
+label: 51
+display_name: "croquet_ball"
+label: 52
+display_name: "crutch"
+label: 53
+display_name: "cucumber"
+label: 54
+display_name: "cup_or_mug"
+label: 55
+display_name: "diaper"
+label: 56
+display_name: "digital_clock"
+label: 57
+display_name: "dishwasher"
+label: 58
+display_name: "dog"
+label: 59
+display_name: "domestic_cat"
+label: 60
+display_name: "dragonfly"
+label: 61
+display_name: "drum"
+label: 62
+display_name: "dumbbell"
+label: 63
+display_name: "electric_fan"
+label: 64
+display_name: "elephant"
+label: 65
+display_name: "face_powder"
+label: 66
+display_name: "fig"
+label: 67
+display_name: "filing_cabinet"
+label: 68
+display_name: "flower_
+label: 69
+display_name: "fl
+label: 70
+display_name: "fox"
+label: 71
+display_name: "french_h
+label: 72
+display_name: "frog"
+label: 73
+display_name: "frying_
+label: 74
+display_name: "giant_pa
+label: 75
+display_name: "goldfish"
+label: 76
+display_name: "golf_ball"
+label: 77
+display_name: "golfcart"
+label: 78
+display_name: "guacamole"
+label: 79
+display_name: "guitar"
+label: 80
+display_name: "hair_dryer"
+label: 81
+display_name: "hair_spray"
+label: 82
+display_name: "hamburger"
+label: 83
+display_name: "hammer"
+label: 84
+display_name: "hamster"
+label: 85
+display_name: "harmonica"
+label: 86
+display_name: "harp"
+label: 87
+display_name: "hat_with_a_wide_brim"
+label: 88
+display_name: "head_cabbage"
+label: 89
+display_name: "helmet"
+label: 90
+display_name: "hippopotamus"
+label: 91
+display_name: "horizontal_bar"
+label: 92
+display_name: "horse"
+label: 93
+display_name: "hotdog"
+label: 94
+display_name: "iPod"
+label: 95
+display_name: "isopod"
+label: 96
+display_name: "jellyfish"
+label: 97
+display_name: "koala_bear"
+label: 98
+display_name: "ladle"
+label: 99
+display_name: "ladybug"
+label: 100
+display_name: "lamp"
+label: 101
+display_name: "laptop"
+label: 102
+display_name: "lemon"
+label: 103
+display_name: "lion"
+label: 104
+display_name: "lipstick"
+label: 105
+display_name: "lizard"
+label: 106
+display_name: "lobster"
+label: 107
+display_name: "maillot"
+label: 108
+display_name: "maraca"
+label: 109
+display_name: "microphone"
+label: 110
+display_name: "microwave"
+label: 111
+display_name: "milk_can"
+label: 112
+display_name: "miniskirt"
+label: 113
+display_name: "monkey"
+label: 114
+display_name: "motorcycle"
+label: 115
+display_name: "mushroom"
+label: 116
+display_name: "nail"
+label: 117
+display_name: "neck_brace"
+label: 118
+display_name: "oboe"
+label: 119
+display_name: "orange"
+label: 120
+display_name: "otter"
+label: 121
+display_name: "pencil_box"
+label: 122
+display_name: "pencil_sharpener"
+label: 123
+display_name: "perfume"
+label: 124
+display_name: "person"
+label: 125
+display_name: "piano"
+label: 126
+display_name: "pineapple"
+label: 127
+display_name: "ping-pong_ball"
+label: 128
+display_name: "pitcher"
+label: 129
+display_name: "pizza"
+label: 130
+display_name: "plastic_bag"
+label: 131
+display_name: "plate_rack"
+label: 132
+display_name: "pomegranate"
+label: 133
+display_name: "popsicle"
+label: 134
+display_name: "porcupine"
+label: 135
+display_name: "power_drill"
+label: 136
+display_name: "pretzel"
+label: 137
+display_name: "printer"
+label: 138
+display_name: "puck"
+label: 139
+display_name: "punching_bag"
+label: 140
+display_name: "purse"
+label: 141
+display_name: "rabbit"
+label: 142
+display_name: "racket"
+label: 143
+display_name: "ray"
+label: 144
+display_name: "red_panda"
+label: 145
+display_name: "refrigerator"
+label: 146
+display_name: "remote_control"
+label: 147
+display_name: "rubber_eraser"
+label: 148
+display_name: "rugby_ball"
+label: 149
+display_name: "ruler"
+label: 150
+display_name: "salt_or_pepper_shaker"
+label: 151
+display_name: "saxophone"
+label: 152
+display_name: "scorpion"
+label: 153
+display_name: "screwdriver"
+label: 154
+display_name: "seal"
+label: 155
+display_name: "sheep"
+label: 156
+display_name: "ski"
+label: 157
+display_name: "skunk"
+label: 158
+display_name: "snail"
+label: 159
+display_name: "snake"
+label: 160
+display_name: "snowmobile"
+label: 161
+display_name: "snowplow"
+label: 162
+display_name: "soap_dispenser"
+label: 163
+display_name: "soccer_ball"
+label: 164
+display_name: "sofa"
+label: 165
+display_name: "spatula"
+label: 166
+display_name: "squirrel"
+label: 167
+display_name: "starfish"
+label: 168
+display_name: "stethoscope"
+label: 169
+display_name: "stove"
+label: 170
+display_name: "strainer"
+label: 171
+display_name: "strawberry"
+label: 172
+display_name: "stretcher"
+label: 173
+display_name: "sunglasses"
+label: 174
+display_name: "swimming_trunks"
+label: 175
+display_name: "swine"
+label: 176
+display_name: "syringe"
+label: 177
+display_name: "table"
+label: 178
+display_name: "tape_player"
+label: 179
+display_name: "tennis_ball"
+label: 180
+display_name: "tick"
+label: 181
+display_name: "tie"
+label: 182
+display_name: "tiger"
+label: 183
+display_name: "toaster"
+label: 184
+display_name: "traffic_light"
+label: 185
+display_name: "train"
+label: 186
+display_name: "trombone"
+label: 187
+display_name: "trumpet"
+label: 188
+display_name: "turtle"
+label: 189
+display_name: "tv_or_monitor"
+label: 190
+display_name: "unicycle"
+label: 191
+display_name: "vacuum"
+label: 192
+display_name: "violin"
+label: 193
+display_name: "volleyball"
+label: 194
+display_name: "waffle_iron"
+label: 195
+display_name: "washer"
+label: 196
+display_name: "water_bottle"
+label: 197
+display_name: "watercraft"
+label: 198
+display_name: "whale"
+label: 199
+display_name: "wine_bottle"
+label: 200
+display_name: "zebra"

大作业/14.2/14.2.py

@@ -0,0 +1,55 @@
+import cv2 as cv
+from PIL import Image
+import pytesseract as tess
+
+
+def recoginse_text(image):
+    """
+    步骤：
+    1、灰度，二值化处理
+    2、形态学操作去噪
+    3、识别
+    :param image:
+    :return:
+    """
+
+    # 灰度 二值化
+    gray = cv.cvtColor(image,cv.COLOR_BGR2GRAY)
+    # 如果是白底黑字 建议 _INV
+    ret,binary = cv.threshold(gray,0,255,cv.THRESH_BINARY_INV| cv.THRESH_OTSU)
+
+
+    # 形态学操作 (根据需要设置参数（1，2）)
+    kernel = cv.getStructuringElement(cv.MORPH_RECT,(1,2))  #去除横向细线
+    morph1 = cv.morphologyEx(binary,cv.MORPH_OPEN,kernel)
+    kernel = cv.getStructuringElement(cv.MORPH_RECT, (2, 1)) #去除纵向细线
+    morph2 = cv.morphologyEx(morph1,cv.MORPH_OPEN,kernel)
+    cv.imshow("Morph",morph2)
+
+    # 黑底白字取非，变为白底黑字（便于pytesseract 识别）
+    cv.bitwise_not(morph2,morph2)
+    textImage = Image.fromarray(morph2)
+
+    # 图片转文字
+    text=tess.image_to_string(textImage)
+    n=10 #根据不同国家车牌固定数目进行设置
+    print("识别结果:")
+    print(text[1:n])
+   
+
+
+def main():
+    # 读取需要识别的数字字母图片，并显示读到的原图
+    src = cv.imread("cp.jpg")
+    cv.imshow("src",src)
+
+    # 识别
+    recoginse_text(src)
+
+    cv.waitKey(0)
+    cv.destroyAllWindows()
+
+if __name__=="__main__":
+    main()
+
+

大作业/14.2/test.pyproj

@@ -0,0 +1,35 @@
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003" ToolsVersion="4.0">
+  <PropertyGroup>
+    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
+    <SchemaVersion>2.0</SchemaVersion>
+    <ProjectGuid>e85e00fb-959d-4c3b-852b-f88a24227bbc</ProjectGuid>
+    <ProjectHome>.</ProjectHome>
+    <StartupFile>test.py</StartupFile>
+    <SearchPath>
+    </SearchPath>
+    <WorkingDirectory>.</WorkingDirectory>
+    <OutputPath>.</OutputPath>
+    <Name>test</Name>
+    <RootNamespace>test</RootNamespace>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)' == 'Debug' ">
+    <DebugSymbols>true</DebugSymbols>
+    <EnableUnmanagedDebugging>false</EnableUnmanagedDebugging>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)' == 'Release' ">
+    <DebugSymbols>true</DebugSymbols>
+    <EnableUnmanagedDebugging>false</EnableUnmanagedDebugging>
+  </PropertyGroup>
+  <ItemGroup>
+    <Compile Include="test.py" />
+  </ItemGroup>
+  <Import Project="$(MSBuildExtensionsPath32)\Microsoft\VisualStudio\v$(VisualStudioVersion)\Python Tools\Microsoft.PythonTools.targets" />
+  <!-- Uncomment the CoreCompile target to enable the Build command in
+       Visual Studio and specify your pre- and post-build commands in
+       the BeforeBuild and AfterBuild targets below. -->
+  <!--<Target Name="CoreCompile" />-->
+  <Target Name="BeforeBuild">
+  </Target>
+  <Target Name="AfterBuild">
+  </Target>
+</Project>

大作业/14.3/14.3.py

@@ -0,0 +1,154 @@
+import tkinter as tk
+from tkinter.filedialog import *
+from tkinter import ttk
+import tkinter.messagebox as mBox
+
+import predict
+import cv2
+from PIL import Image, ImageTk
+import threading
+import time
+
+
+
+class Surface(ttk.Frame):
+	pic_path = ""
+	viewhigh = 600
+	viewwide = 600
+	update_time = 0
+	thread = None
+	thread_run = False
+	camera = None
+	color_transform = {"green":("绿牌","#55FF55"), "yello":("黄牌","#FFFF00"), "blue":("蓝牌","#6666FF")}
+		
+	def __init__(self, win):
+		ttk.Frame.__init__(self, win)
+		frame_left = ttk.Frame(self)
+		frame_right1 = ttk.Frame(self)
+		frame_right2 = ttk.Frame(self)
+		win.title("车牌识别")
+		win.state("zoomed")
+		self.pack(fill=tk.BOTH, expand=tk.YES, padx="5", pady="5")
+		frame_left.pack(side=tk.LEFT,expand=1,fill=tk.BOTH)
+		frame_right1.pack(side=tk.TOP,expand=1,fill=tk.Y)
+		frame_right2.pack(side=tk.RIGHT,expand=0)
+		ttk.Label(frame_left, text='原图：').pack(anchor="nw") 
+		ttk.Label(frame_right1, text='车牌位置：').grid(column=0, row=0, sticky=tk.W)
+		
+		from_pic_ctl = ttk.Button(frame_right2, text="来自图片", width=20, command=self.from_pic)
+		from_vedio_ctl = ttk.Button(frame_right2, text="来自摄像头", width=20, command=self.from_vedio)
+		self.image_ctl = ttk.Label(frame_left)
+		self.image_ctl.pack(anchor="nw")
+		
+		self.roi_ctl = ttk.Label(frame_right1)
+		self.roi_ctl.grid(column=0, row=1, sticky=tk.W)
+		ttk.Label(frame_right1, text='识别结果：').grid(column=0, row=2, sticky=tk.W)
+		self.r_ctl = ttk.Label(frame_right1, text="")
+		self.r_ctl.grid(column=0, row=3, sticky=tk.W)
+		self.color_ctl = ttk.Label(frame_right1, text="", width="20")
+		self.color_ctl.grid(column=0, row=4, sticky=tk.W)
+		from_vedio_ctl.pack(anchor="se", pady="5")
+		from_pic_ctl.pack(anchor="se", pady="5")
+		self.predictor = predict.CardPredictor()
+		self.predictor.train_svm()
+		
+	def get_imgtk(self, img_bgr):
+		img = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
+		im = Image.fromarray(img)
+		imgtk = ImageTk.PhotoImage(image=im)
+		wide = imgtk.width()
+		high = imgtk.height()
+		if wide > self.viewwide or high > self.viewhigh:
+			wide_factor = self.viewwide / wide
+			high_factor = self.viewhigh / high
+			factor = min(wide_factor, high_factor)
+			
+			wide = int(wide * factor)
+			if wide <= 0 : wide = 1
+			high = int(high * factor)
+			if high <= 0 : high = 1
+			im=im.resize((wide, high), Image.LANCZOS) #在pillow的10.0.0版本中，ANTIALIAS方法被删除了，使用新的方法即可：
+			imgtk = ImageTk.PhotoImage(image=im)
+		return imgtk
+	
+	def show_roi(self, r, roi, color):
+		if r :
+			roi = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
+			roi = Image.fromarray(roi)
+			self.imgtk_roi = ImageTk.PhotoImage(image=roi)
+			self.roi_ctl.configure(image=self.imgtk_roi, state='enable')
+			self.r_ctl.configure(text=str(r))
+			self.update_time = time.time()
+			try:
+				c = self.color_transform[color]
+				self.color_ctl.configure(text=c[0], background=c[1], state='enable')
+			except: 
+				self.color_ctl.configure(state='disabled')
+		elif self.update_time + 8 < time.time():
+			self.roi_ctl.configure(state='disabled')
+			self.r_ctl.configure(text="")
+			self.color_ctl.configure(state='disabled')
+		
+	def from_vedio(self):
+		if self.thread_run:
+			return
+		if self.camera is None:
+			self.camera = cv2.VideoCapture(0)
+			if not self.camera.isOpened():
+				mBox.showwarning('警告', '摄像头打开失败！')
+				self.camera = None
+				return
+		self.thread = threading.Thread(target=self.vedio_thread, args=(self,))
+		self.thread.setDaemon(True)
+		self.thread.start()
+		self.thread_run = True
+		
+	def from_pic(self):
+		self.thread_run = False
+		self.pic_path = askopenfilename(title="选择识别图片", filetypes=[("jpg图片", "*.jpg")])
+		if self.pic_path:
+			img_bgr = predict.imreadex(self.pic_path)
+			self.imgtk = self.get_imgtk(img_bgr)
+			self.image_ctl.configure(image=self.imgtk)
+			resize_rates = (1, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4)
+			for resize_rate in resize_rates:
+				print("resize_rate:", resize_rate)
+				try:
+					r, roi, color = self.predictor.predict(img_bgr, resize_rate)
+				except:
+					continue
+				if r:
+					break
+			#r, roi, color = self.predictor.predict(img_bgr, 1)
+			self.show_roi(r, roi, color)
+
+	@staticmethod
+	def vedio_thread(self):
+		self.thread_run = True
+		predict_time = time.time()
+		while self.thread_run:
+			_, img_bgr = self.camera.read()
+			self.imgtk = self.get_imgtk(img_bgr)
+			self.image_ctl.configure(image=self.imgtk)
+			if time.time() - predict_time > 2:
+				r, roi, color = self.predictor.predict(img_bgr)
+				self.show_roi(r, roi, color)
+				predict_time = time.time()
+		print("run end")
+		
+		
+def close_window():
+	print("destroy")
+	if surface.thread_run :
+		surface.thread_run = False
+		surface.thread.join(2.0)
+	win.destroy()
+	
+	
+if __name__ == '__main__':
+	win=tk.Tk()
+	
+	surface = Surface(win)
+	win.protocol('WM_DELETE_WINDOW', close_window)
+	win.mainloop()
+	

大作业/14.3/config.js

@@ -0,0 +1,20 @@
+{
+	"config":[
+	{
+		"open":1,
+		"blur":3,
+		"morphologyr":4,
+		"morphologyc":19,
+		"col_num_limit":10,
+		"row_num_limit":21
+	},
+	{
+		"open":0,
+		"blur":3,
+		"morphologyr":5,
+		"morphologyc":12,
+		"col_num_limit":10,
+		"row_num_limit":18
+	}
+	]
+}

大作业/14.3/labelmap_det.txt

@@ -0,0 +1,402 @@
+label: 0
+display_name: "background"
+label: 1
+display_name: "accordion"
+label: 2
+display_name: "airplane"
+label: 3
+display_name: "ant"
+label: 4
+display_name: "antelope"
+label: 5
+display_name: "apple"
+label: 6
+display_name: "armadillo"
+label: 7
+display_name: "artichoke"
+label: 8
+display_name: "axe"
+label: 9
+display_name: "baby_bed"
+label: 10
+display_name: "backpack"
+label: 11
+display_name: "bagel"
+label: 12
+display_name: "balance_beam"
+label: 13
+display_name: "banana"
+label: 14
+display_name: "band_aid"
+label: 15
+display_name: "banjo"
+label: 16
+display_name: "baseball"
+label: 17
+display_name: "basketball"
+label: 18
+display_name: "bathing_cap"
+label: 19
+display_name: "beaker"
+label: 20
+display_name: "bear"
+label: 21
+display_name: "bee"
+label: 22
+display_name: "bell_pepper"
+label: 23
+display_name: "bench"
+label: 24
+display_name: "bicycle"
+label: 25
+display_name: "binder"
+label: 26
+display_name: "bird"
+label: 27
+display_name: "bookshelf"
+label: 28
+display_name: "bow_tie"
+label: 29
+display_name: "bow"
+label: 30
+display_name: "bowl"
+label: 31
+display_name: "brassiere"
+label: 32
+display_name: "burrito"
+label: 33
+display_name: "bus"
+label: 34
+display_name: "butterfly"
+label: 35
+display_name: "camel"
+label: 36
+display_name: "can_opener"
+label: 37
+display_name: "car"
+label: 38
+display_name: "cart"
+label: 39
+display_name: "cattle"
+label: 40
+display_name: "cello"
+label: 41
+display_name: "centipede"
+label: 42
+display_name: "chain_saw"
+label: 43
+display_name: "chair"
+label: 44
+display_name: "chime"
+label: 45
+display_name: "cocktail_shaker"
+label: 46
+display_name: "coffee_maker"
+label: 47
+display_name: "computer_keyboard"
+label: 48
+display_name: "computer_mouse"
+label: 49
+display_name: "corkscrew"
+label: 50
+display_name: "cream"
+label: 51
+display_name: "croquet_ball"
+label: 52
+display_name: "crutch"
+label: 53
+display_name: "cucumber"
+label: 54
+display_name: "cup_or_mug"
+label: 55
+display_name: "diaper"
+label: 56
+display_name: "digital_clock"
+label: 57
+display_name: "dishwasher"
+label: 58
+display_name: "dog"
+label: 59
+display_name: "domestic_cat"
+label: 60
+display_name: "dragonfly"
+label: 61
+display_name: "drum"
+label: 62
+display_name: "dumbbell"
+label: 63
+display_name: "electric_fan"
+label: 64
+display_name: "elephant"
+label: 65
+display_name: "face_powder"
+label: 66
+display_name: "fig"
+label: 67
+display_name: "filing_cabinet"
+label: 68
+display_name: "flower_
+label: 69
+display_name: "fl
+label: 70
+display_name: "fox"
+label: 71
+display_name: "french_h
+label: 72
+display_name: "frog"
+label: 73
+display_name: "frying_
+label: 74
+display_name: "giant_pa
+label: 75
+display_name: "goldfish"
+label: 76
+display_name: "golf_ball"
+label: 77
+display_name: "golfcart"
+label: 78
+display_name: "guacamole"
+label: 79
+display_name: "guitar"
+label: 80
+display_name: "hair_dryer"
+label: 81
+display_name: "hair_spray"
+label: 82
+display_name: "hamburger"
+label: 83
+display_name: "hammer"
+label: 84
+display_name: "hamster"
+label: 85
+display_name: "harmonica"
+label: 86
+display_name: "harp"
+label: 87
+display_name: "hat_with_a_wide_brim"
+label: 88
+display_name: "head_cabbage"
+label: 89
+display_name: "helmet"
+label: 90
+display_name: "hippopotamus"
+label: 91
+display_name: "horizontal_bar"
+label: 92
+display_name: "horse"
+label: 93
+display_name: "hotdog"
+label: 94
+display_name: "iPod"
+label: 95
+display_name: "isopod"
+label: 96
+display_name: "jellyfish"
+label: 97
+display_name: "koala_bear"
+label: 98
+display_name: "ladle"
+label: 99
+display_name: "ladybug"
+label: 100
+display_name: "lamp"
+label: 101
+display_name: "laptop"
+label: 102
+display_name: "lemon"
+label: 103
+display_name: "lion"
+label: 104
+display_name: "lipstick"
+label: 105
+display_name: "lizard"
+label: 106
+display_name: "lobster"
+label: 107
+display_name: "maillot"
+label: 108
+display_name: "maraca"
+label: 109
+display_name: "microphone"
+label: 110
+display_name: "microwave"
+label: 111
+display_name: "milk_can"
+label: 112
+display_name: "miniskirt"
+label: 113
+display_name: "monkey"
+label: 114
+display_name: "motorcycle"
+label: 115
+display_name: "mushroom"
+label: 116
+display_name: "nail"
+label: 117
+display_name: "neck_brace"
+label: 118
+display_name: "oboe"
+label: 119
+display_name: "orange"
+label: 120
+display_name: "otter"
+label: 121
+display_name: "pencil_box"
+label: 122
+display_name: "pencil_sharpener"
+label: 123
+display_name: "perfume"
+label: 124
+display_name: "person"
+label: 125
+display_name: "piano"
+label: 126
+display_name: "pineapple"
+label: 127
+display_name: "ping-pong_ball"
+label: 128
+display_name: "pitcher"
+label: 129
+display_name: "pizza"
+label: 130
+display_name: "plastic_bag"
+label: 131
+display_name: "plate_rack"
+label: 132
+display_name: "pomegranate"
+label: 133
+display_name: "popsicle"
+label: 134
+display_name: "porcupine"
+label: 135
+display_name: "power_drill"
+label: 136
+display_name: "pretzel"
+label: 137
+display_name: "printer"
+label: 138
+display_name: "puck"
+label: 139
+display_name: "punching_bag"
+label: 140
+display_name: "purse"
+label: 141
+display_name: "rabbit"
+label: 142
+display_name: "racket"
+label: 143
+display_name: "ray"
+label: 144
+display_name: "red_panda"
+label: 145
+display_name: "refrigerator"
+label: 146
+display_name: "remote_control"
+label: 147
+display_name: "rubber_eraser"
+label: 148
+display_name: "rugby_ball"
+label: 149
+display_name: "ruler"
+label: 150
+display_name: "salt_or_pepper_shaker"
+label: 151
+display_name: "saxophone"
+label: 152
+display_name: "scorpion"
+label: 153
+display_name: "screwdriver"
+label: 154
+display_name: "seal"
+label: 155
+display_name: "sheep"
+label: 156
+display_name: "ski"
+label: 157
+display_name: "skunk"
+label: 158
+display_name: "snail"
+label: 159
+display_name: "snake"
+label: 160
+display_name: "snowmobile"
+label: 161
+display_name: "snowplow"
+label: 162
+display_name: "soap_dispenser"
+label: 163
+display_name: "soccer_ball"
+label: 164
+display_name: "sofa"
+label: 165
+display_name: "spatula"
+label: 166
+display_name: "squirrel"
+label: 167
+display_name: "starfish"
+label: 168
+display_name: "stethoscope"
+label: 169
+display_name: "stove"
+label: 170
+display_name: "strainer"
+label: 171
+display_name: "strawberry"
+label: 172
+display_name: "stretcher"
+label: 173
+display_name: "sunglasses"
+label: 174
+display_name: "swimming_trunks"
+label: 175
+display_name: "swine"
+label: 176
+display_name: "syringe"
+label: 177
+display_name: "table"
+label: 178
+display_name: "tape_player"
+label: 179
+display_name: "tennis_ball"
+label: 180
+display_name: "tick"
+label: 181
+display_name: "tie"
+label: 182
+display_name: "tiger"
+label: 183
+display_name: "toaster"
+label: 184
+display_name: "traffic_light"
+label: 185
+display_name: "train"
+label: 186
+display_name: "trombone"
+label: 187
+display_name: "trumpet"
+label: 188
+display_name: "turtle"
+label: 189
+display_name: "tv_or_monitor"
+label: 190
+display_name: "unicycle"
+label: 191
+display_name: "vacuum"
+label: 192
+display_name: "violin"
+label: 193
+display_name: "volleyball"
+label: 194
+display_name: "waffle_iron"
+label: 195
+display_name: "washer"
+label: 196
+display_name: "water_bottle"
+label: 197
+display_name: "watercraft"
+label: 198
+display_name: "whale"
+label: 199
+display_name: "wine_bottle"
+label: 200
+display_name: "zebra"

大作业/requirements.txt

@@ -0,0 +1,4 @@
+opencv-python~=4.10.0.84
+numpy~=1.21.6
+pytesseract~=0.3.10
+pillow~=9.5.0

实验八/README.MD

@@ -0,0 +1,35 @@
+# 简单的人脸识别
+
+## 玩法
+
+###  配置环境
+
+#### 1.安装requirements.txt
+
+```bash
+pip install -r requirements.txt
+```
+
+#### 2.下载dlib模型
+
+只需执行我的自动下载脚本即可，需`魔法上网`
+
+```bash
+./init_enviorment.sh
+```
+
+```powershell
+.\init_enviorment.ps1
+```
+
+### 替换数据集
+
+- 替换`cache\dataset.mp4`
+
+- 录一段你想要识别为True的人脸的视频
+
+- 然后训练
+
+### 测试图片路径
+
+测试图片在`cache`文件夹内，一个`positive.jpg`，一个`negative.jpg`，分别是正负样本

实验八/detect.py

@@ -0,0 +1,78 @@
+import cv2 as cv
+import numpy as np
+import dlib
+import joblib
+
+
+# 画框函数
+def draw_rect(img, faces):
+    for face in faces:
+        cv.rectangle(img, (face.left(), face.top()), (face.right(), face.bottom()), (0, 0, 255), 32)
+        return img
+
+
+# 检测人脸并画框
+def detect_face(img):
+    img_gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
+    result = detector(img_gray, 1)
+    img_result = draw_rect(img, result)
+    return img_result
+
+
+# 提取人脸特征
+def extract_face_feature(img):
+    faces = detector(img)
+    if len(faces) > 0:
+        face = faces[0]
+        landmarks = predictor(img, face)
+        face_descriptor = face_rec_model.compute_face_descriptor(img, landmarks)
+        return np.array(face_descriptor)
+    else:
+        return None
+
+
+# 加载分类器
+classifier = joblib.load('models/classifier.pkl')
+
+# 读取测试图片
+positive_sample = cv.imread('cache/positive_test.jpg')
+positive_sample_rgb = cv.cvtColor(positive_sample, cv.COLOR_BGR2RGB)
+
+negative_sample = cv.imread('cache/love.jpg')
+negative_sample_rgb = cv.cvtColor(negative_sample, cv.COLOR_BGR2RGB)
+
+# 加载dlib人脸检测模型
+detector = dlib.get_frontal_face_detector()
+predictor = dlib.shape_predictor("models/shape_predictor_68_face_landmarks_GTX.dat")
+face_rec_model = dlib.face_recognition_model_v1('models/dlib_face_recognition_resnet_model_v1.dat')
+
+# 检测人脸
+positive_result = detect_face(positive_sample)
+negative_result = detect_face(negative_sample)
+
+# 计算人脸特征
+positive_feature = extract_face_feature(positive_sample_rgb)
+positive_feature = np.array(positive_feature).reshape(1, -1)
+
+negative_feature = extract_face_feature(negative_sample_rgb)
+negative_feature = np.array(negative_feature).reshape(1, -1)
+
+# 通过分类器预测
+positive_predict = classifier.predict(positive_feature)
+negative_predict = classifier.predict(negative_feature)
+
+# 展示
+positive_result_resized = cv.resize(positive_result,
+                                    (int(positive_result.shape[1] * 0.1), int(positive_result.shape[0] * 0.1)))
+positive_result_resized = cv.putText(positive_result_resized, str(positive_predict), (50, 50), cv.FONT_HERSHEY_SIMPLEX,
+                                     1, (0, 0, 255), 2)
+
+negative_result_resized = cv.resize(negative_result,
+                                    (int(negative_result.shape[1] * 0.1), int(negative_result.shape[0] * 0.1)))
+negative_result_resized = cv.putText(negative_result_resized, str(negative_predict), (50, 50), cv.FONT_HERSHEY_SIMPLEX,
+                                     1, (0, 0, 255), 2)
+
+cv.imshow('positive_result', positive_result_resized)
+cv.imshow('negative_result', negative_result_resized)
+cv.waitKey(0)
+cv.destroyAllWindows()

实验八/init_enviorment.ps1

@@ -0,0 +1,10 @@
+mkdir models
+mkdir cache
+wget https://github.com/davisking/dlib-models/raw/refs/heads/master/shape_predictor_68_face_landmarks_GTX.dat.bz2
+wget https://github.com/davisking/dlib-models/raw/refs/heads/master/dlib_face_recognition_resnet_model_v1.dat.bz2
+Move-Item dlib_face_recognition_resnet_model_v1.dat.bz2 models/
+Move-Item shape_predictor_68_face_landmarks_GTX.dat.bz2 models/
+Set-Location models
+7z x dlib_face_recognition_resnet_model_v1.dat.bz2
+7z x shape_predictor_68_face_landmarks_GTX.dat.bz2
+Write-Output initialized enviorment!

实验八/init_enviorment.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+wget https://github.com/davisking/dlib-models/raw/refs/heads/master/shape_predictor_68_face_landmarks_GTX.dat.bz2
+wget https://github.com/davisking/dlib-models/raw/refs/heads/master/dlib_face_recognition_resnet_model_v1.dat.bz2
+mkdir cache
+mkdir models
+mv dlib_face_recognition_resnet_model_v1.dat.bz2 models/
+mv shape_predictor_68_face_landmarks_GTX.dat.bz2 models/
+cd models
+bzip2 -d dlib_face_recognition_resnet_model_v1.dat.bz2
+bzip2 -d shape_predictor_68_face_landmarks_GTX.dat.bz2
+echo initialized enviorment!

实验八/train.py

@@ -0,0 +1,101 @@
+import cv2
+import cv2 as cv
+import dlib
+import joblib
+import numpy as np
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
+from sklearn.svm import SVC
+from tqdm import tqdm
+
+
+# 方法区
+## 转换为二值图和RGB图
+def img_cvt(img):
+    img_gray = cv.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    _, img_gray = cv.threshold(img_gray, 127, 255, cv.THRESH_BINARY)
+    img_gray = cv.blur(img_gray, (3, 3))
+    img_rgb = cv.cvtColor(img, cv.COLOR_BGR2RGB)
+    return img_gray, img_rgb
+
+
+## 提取人脸特征
+def extract_face_feature(img):
+    faces = detector(img)
+    if len(faces) > 0:
+        face = faces[0]
+        landmarks = predictor(img, face)
+        face_descriptor = face_rec_model.compute_face_descriptor(img, landmarks)
+        return np.array(face_descriptor)
+    else:
+        return None
+
+
+## 生成伪样品
+def gen_negative_samples(features_dim=128):
+    return np.random.uniform(-1, 1, features_dim)
+
+
+# 变量区
+dataset_video = cv.VideoCapture('cache/dataset.mp4')
+datasets = []
+datasets_rgb = []
+features = []
+negative_samples = []
+
+# 收集数据集
+## 采用视频的格式收集图片
+while (True):
+    ret, frame = dataset_video.read()
+    if not ret:
+        break
+    datasets.append(frame)
+
+# 加载人脸检测模型
+detector = dlib.get_frontal_face_detector()
+predictor = dlib.shape_predictor("models/shape_predictor_68_face_landmarks_GTX.dat")
+face_rec_model = dlib.face_recognition_model_v1('models/dlib_face_recognition_resnet_model_v1.dat')
+
+# 预处理数据集
+for dataset in tqdm(datasets, desc='正在预处理数据集'):
+    _, dataset_rgb = img_cvt(dataset)
+    datasets_rgb.append(dataset_rgb)
+
+# 求人脸特征
+for dataset in tqdm(datasets_rgb, desc='正在求人脸特征'):
+    face_descriptor = extract_face_feature(dataset)
+    if face_descriptor is not None:
+        features.append(face_descriptor)
+
+# 生成负样本
+for i in tqdm(range(len(features) * 75), desc='正在生成负样本'):
+    negative_sample = gen_negative_samples()
+    negative_samples.append(negative_sample)
+
+# 编码数据集
+positive_labels = [1] * len(features)
+negative_labels = [0] * len(negative_samples)
+
+samples = features + negative_samples
+labels = positive_labels + negative_labels
+
+X_train = np.array(samples)
+Y_train = np.array(labels)
+
+# 分离数据集和训练集
+X_train, X_test, Y_train, Y_test = train_test_split(X_train, Y_train, test_size=0.2, random_state=42, stratify=Y_train)
+
+# 训练
+print('正在训练分类器')
+classifier = SVC(kernel='linear', C=1.0, random_state=42)
+classifier.fit(X_train, Y_train)
+
+# 评估分类器性能
+Y_pred = []
+for test_sample in tqdm(X_test, desc='评估分类器'):
+    Y_pred.append(classifier.predict(test_sample.reshape(1, -1)))
+accuracy = accuracy_score(Y_test, Y_pred)
+print(f'准确率：{accuracy * 100:.5f}%')
+
+# 保存模型
+joblib.dump(classifier, 'models/classifier.pkl')