opencv图像处理—项目实战：答题卡识别判卷

---

 

哔站唐宇迪opencv课程——项目实战：答题卡识别判卷

【计算机视觉-OpenCV】唐宇迪博士教会了我大学四年没学会的OpenCV OpenCV计算机视觉实战全套课程（附带课程课件资料+课件笔记+源码）_哔哩哔哩_bilibili 

---

 

目录

Step1 预处理 

1.1高斯滤波 

 1.2边缘检测

 1.3轮廓检测

Step2透视变换 

2.1 four_point_transform

2.2 order_points 

Step3 二值处理

 Step4

4.1寻找圆圈轮廓 

 4.2寻找选项轮廓

 4.3选项轮廓从上到下排序

 4.3.1 sort_contours

Step5输出结果

Step6打印操作

完整代码

---

方法：试卷扫描-轮廓检测-对每一个位置指定掩码 -统计里面非零值大小-哪个选项值最大就选的是哪个

 导入工具包

import numpy as np
import argparse
import imutils
import cv2

 设置参数

ap=argparse.ArgumentParser()
ap.add_argument("-i","--image",required=True,help="path to the input image")
args=vars(ap.parse_args())

正确答案 

# 正确答案
ANSWER_KEY = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}

绘图函数 

def cv_show(name,img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

 

 

---

Step1 预处理 

1.1高斯滤波 

#预处理
image = cv2.imread(args["image"])
contours_img = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)#灰度
blurred = cv2.GaussianBlur(gray,(5,5),0)#高斯滤波去噪音
cv_show('blurred',blurred)

高斯滤波 ：

 1.2边缘检测

#边缘检测
edges = cv2.Canny(blurred,75,200)
cv_show("edges",edges)

 边缘检测：

 1.3轮廓检测

#轮廓检测
cnts = cv2.findContours(edges.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(contours_img,cnts,-1,(0,0,255),3)
cv_show("contours_img",contours_img)
docCnt = None

 

 轮廓检测：

 

 

Step2透视变换 

#确保检测到了
if len(cnts) > 0:
    #根据轮廓大小进行排序
    cnts = sorted(cnts,key=cv2.contourArea,reverse=True)
    
    #遍历每一个轮廓
    for c in cnts:
        #近似
        peri = cv2.arcLength(c,True)
        approx = cv2.approxPolyDP(c,0.02*peri,True) #近似轮廓
        
        # 准备做透视变换
        if len(approx) == 4:
            docCnt = approx
            break #找到了做透视变换的四个坐标了
#执行透视变换
warped = four_point_transform(gray,docCnt.reshape(4,2))
cv_show("warped",warped)

2.1 four_point_transform

def four_point_transform(image,pts):
    #获取输入坐标点
    rect = order_points(pts)
    (tl,tr,br,bl) = rect
    
    #计算输入的w和h值
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA),int(widthB))
    
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA),int(heightB))

    #变换后对应坐标位置
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")
    
    #计算变换矩阵
    M = cv2.getPerspectiveTransform(rect,dst)
    warped = cv2.warpPerspective(image,M,(maxWidth,maxHeight))
    
    #返回变换后结果
    return warped

2.2 order_points 

def order_points(pts):
#根据位置信息定位四个坐标点的位置
    rect = np.zeros((4,2),dtype="float32")
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]
    diff = np.diff(pts,axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]
    return rect

 透视变换：

 

 

Step3 二值处理

#0tsu's阈值处理
#参数：预处理好的图像、0：自动判断、cv2.THRESH_OTSU：自适应
thresh=cv2.threshold(warped,0,255,cv2.THRESH_BINARY_INV|cv2.THRESH_OTSU)[1]
cv_show('thresh',thresh)

 二值结果：

 Step4

4.1寻找圆圈轮廓 

thresh_Contours=thresh.copy()
#找到每一个圆圈轮廓
cnts=cv2.findContours(thresh.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(thresh_Contours,cnts,-1,(0,0,255),3)
cv_show('thresh_Contours',thresh_Contours)

 

 4.2寻找选项轮廓

questionCnts = []
#遍历
for c in cnts:
    #计算比例和大小
    (x,y,w,h) = cv2.boundingRect(c)#圆形的外接矩形
    ar = w/float(h)#宽和长的比值
    
    #根据实际情况设定标准
    if w>=20 and h>=20 and ar>=0.9 and ar<=1.1:
        questionCnts.append(c)

 

 4.3选项轮廓从上到下排序

#将每一个圆形的轮廓按照从上到下进行排序
questionCnts = sort_contours(questionCnts,method="top-to-bottom")[0]

 4.3.1 sort_contours

def sort_contours(cnts,method="left-to-right"):
    reverse = False
    i = 0
    if method == "right-to-left" or method == "bottom-to-top":
        reverse = True
    if method == "top-to-bottom" or method == "bottom-to-top":
        i = 1
    
    # 计算外接矩形 boundingBoxes是一个元组
    boundingBoxes = [cv2.boundingRect(c) for c in cnts]#用一个最小的矩形，把找到的形状包起来x,y,h,w
    
    # sorted排序
    (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
                                        key=lambda b: b[1][i], reverse=reverse))
    return cnts,boundingBoxes# 轮廓和boundingBoxess

 

Step5输出结果

给每个题的五个轮廓从左到右排序，每个选项做掩码，与操作，统计选项里面非零值大小，哪个选项值最大就选的是哪个，记录下来与正确选项对比，计算正确的个数。

correct=0
for (q,i) in enumerate(np.arange(0,len(questionCnts),5)):
    #排序
    cnts = sort_contours(questionCnts[i:i+5])[0]
    bubble = None
    
    #遍历每一个结果
    for (j,c) in enumerate(cnts):
        #使用mask来判断结果
        mask = np.zeros(thresh.shape,dtype="uint8")
        cv2.drawContours(mask,[c],-1,255,-1)#-1表示填充
        cv_show('mask',mask)
        #通过计算非零像素点的数量来算是否选择这个答案
        mask = cv2.bitwise_and(thresh,thresh,mask=mask)
        #通过与操作，只保留了掩码为白色的那一个部分
        cv_show('mask',mask)
        total = cv2.countNonZero(mask)
        
        #通过阈值判断
        if bubble is None or total>bubble[0]:
            bubble = (total,j)
    
    #对比正确答案
    color = (0,0,255)
    k = ANSWER_KEY[q] #q代表现在检查的是第q个题

    #k是正确答案
    if k == bubble[1]:
        color = (0,255,0)
        correct += 1

 

Step6打印操作

    
#绘图
cv2.drawContours(warped,[cnts[k]],-1,color,3)

score = (correct/5.0) * 100
print("[INFO] score:{:.2f}%".format(score)) #这个%只是为了显示为60%，没有其他意思
cv2.putText(warped,"{:.2f}%".format(score),(10,30),cv2.FONT_HERSHEY_SIMPLEX,0.9,3)
cv_show("Original",image)
cv_show("Exam",warped)

 

 

 

---

完整代码

import numpy as np
import argparse
import imutils
import cv2

ap = argparse.ArgumentParser()
ap.add_argument("-i","--image",required=True,help="path to the input image")
args = vars(ap.parse_args())

# 正确答案
ANSWER_KEY = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}


def order_points(pts):
    # 一共4个坐标点
    rect = np.zeros((4, 2), dtype="float32")

    # 按顺序找到对应坐标0123分别是 左上，右上，右下，左下
    # 计算左上，右下
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]

    # 计算右上和左下
    diff = np.diff(pts, axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]

    return rect


def four_point_transform(image, pts):
    # 获取输入坐标点
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # 计算输入的w和h值
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # 变换后对应坐标位置
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # 计算变换矩阵
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # 返回变换后结果
    return warped


def sort_contours(cnts, method="left-to-right"):
    reverse = False
    i = 0
    if method == "right-to-left" or method == "bottom-to-top":
        reverse = True
    if method == "top-to-bottom" or method == "bottom-to-top":
        i = 1
    boundingBoxes = [cv2.boundingRect(c) for c in cnts]
    (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
                                        key=lambda b: b[1][i], reverse=reverse))
    return cnts, boundingBoxes


def cv_show(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


# 预处理
image = cv2.imread(args["image"])
contours_img = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
cv_show('blurred', blurred)
edged = cv2.Canny(blurred, 75, 200)
cv_show('edged', edged)

# 轮廓检测
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
                        cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(contours_img, cnts, -1, (0, 0, 255), 3)
cv_show('contours_img', contours_img)
docCnt = None

# 确保检测到了
if len(cnts) > 0:
    # 根据轮廓大小进行排序
    cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

    # 遍历每一个轮廓
    for c in cnts:
        # 近似
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)

        # 准备做透视变换
        if len(approx) == 4:
            docCnt = approx
            break

# 执行透视变换

warped = four_point_transform(gray, docCnt.reshape(4, 2))
cv_show('warped', warped)
# Otsu's 阈值处理
thresh = cv2.threshold(warped, 0, 255,
                       cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
cv_show('thresh', thresh)
thresh_Contours = thresh.copy()
# 找到每一个圆圈轮廓
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
                        cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(thresh_Contours, cnts, -1, (0, 0, 255), 3)
cv_show('thresh_Contours', thresh_Contours)
questionCnts = []

# 遍历
for c in cnts:
    # 计算比例和大小
    (x, y, w, h) = cv2.boundingRect(c)
    ar = w / float(h)

    # 根据实际情况指定标准
    if w >= 20 and h >= 20 and ar >= 0.9 and ar <= 1.1:
        questionCnts.append(c)

# 按照从上到下进行排序
questionCnts = sort_contours(questionCnts,
                             method="top-to-bottom")[0]
correct = 0

# 每排有5个选项
for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
    # 排序
    cnts = sort_contours(questionCnts[i:i + 5])[0]
    bubbled = None

    # 遍历每一个结果
    for (j, c) in enumerate(cnts):
        # 使用mask来判断结果
        mask = np.zeros(thresh.shape, dtype="uint8")
        cv2.drawContours(mask, [c], -1, 255, -1)  # -1表示填充
        cv_show('mask', mask)
        # 通过计算非零点数量来算是否选择这个答案
        mask = cv2.bitwise_and(thresh, thresh, mask=mask)
        cv_show('mask', mask)
        total = cv2.countNonZero(mask)

        # 通过阈值判断
        if bubbled is None or total > bubbled[0]:
            bubbled = (total, j)

    # 对比正确答案
    color = (0, 0, 255)
    k = ANSWER_KEY[q]

    # 判断正确
    if k == bubbled[1]:
        color = (0, 255, 0)
        correct += 1

    # 绘图
    cv2.drawContours(warped, [cnts[k]], -1, color, 3)

score = (correct / 5.0) * 100
print("[INFO] score: {:.2f}%".format(score))
cv2.putText(warped, "{:.2f}%".format(score), (10, 30),
            cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
cv2.imshow("Original", image)
cv2.imshow("Exam", warped)
cv2.waitKey(0)