使用 OpenCV-Python 識別答題卡判卷功能

Posted on by

任務

識別用相機拍下來的答題卡，並判斷最終得分（假設正確答案是B, E, A, D, B）

主要步驟

  1. 輪廓識別——答題卡邊緣識別
  2. 透視變換——提取答題卡主體
  3. 輪廓識別——識別出所有圓形選項，剔除無關輪廓
  4. 檢測每一行選擇的是哪一項，並將結果儲存起來，記錄正確的個數
  5. 計算最終得分並在圖中標註

分步實現

輪廓識別——答題卡邊緣識別

輸入圖像

import cv2 as cv
import numpy as np
 
# 正確答案
right_key = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}
 
# 輸入圖像
img = cv.imread('./images/test_01.jpg')
img_copy = img.copy()
img_gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
cvshow('img-gray', img_gray)

圖像預處理

# 圖像預處理
# 高斯降噪
img_gaussian = cv.GaussianBlur(img_gray, (5, 5), 1)
cvshow('gaussianblur', img_gaussian)
# canny邊緣檢測
img_canny = cv.Canny(img_gaussian, 80, 150)
cvshow('canny', img_canny)

 

 

輪廓識別——答題卡邊緣識別

# 輪廓識別——答題卡邊緣識別
cnts, hierarchy = cv.findContours(img_canny, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
cv.drawContours(img_copy, cnts, -1, (0, 0, 255), 3)
cvshow('contours-show', img_copy)

透視變換——提取答題卡主體

對每個輪廓進行擬合，將多邊形輪廓變為四邊形

docCnt = None
 
# 確保檢測到瞭
if len(cnts) > 0:
    # 根據輪廓大小進行排序
    cnts = sorted(cnts, key=cv.contourArea, reverse=True)
 
    # 遍歷每一個輪廓
    for c in cnts:
        # 近似
        peri = cv.arcLength(c, True)
        # arclength 計算一段曲線的長度或者閉合曲線的周長；
        # 第一個參數輸入一個二維向量，第二個參數表示計算曲線是否閉合
 
        approx = cv.approxPolyDP(c, 0.02 * peri, True)
        # 用一條頂點較少的曲線/多邊形來近似曲線/多邊形，以使它們之間的距離<=指定的精度；
        # c是需要近似的曲線，0.02*peri是精度的最大值，True表示曲線是閉合的
 
        # 準備做透視變換
        if len(approx) == 4:
            docCnt = approx
            break

透視變換——提取答題卡主體

# 透視變換——提取答題卡主體
docCnt = docCnt.reshape(4, 2)
warped = four_point_transform(img_gray, docCnt)
cvshow('warped', warped)
def four_point_transform(img, four_points):
    rect = order_points(four_points)
    (tl, tr, br, bl) = rect
 
    # 計算輸入的w和h的值
    widthA = np.sqrt((tr[0] - tl[0]) ** 2 + (tr[1] - tl[1]) ** 2)
    widthB = np.sqrt((br[0] - bl[0]) ** 2 + (br[1] - bl[1]) ** 2)
    maxWidth = max(int(widthA), int(widthB))
 
    heightA = np.sqrt((tl[0] - bl[0]) ** 2 + (tl[1] - bl[1]) ** 2)
    heightB = np.sqrt((tr[0] - br[0]) ** 2 + (tr[1] - br[1]) ** 2)
    maxHeight = max(int(heightA), int(heightB))
 
    # 變換後對應的坐標位置
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype='float32')
 
    # 最主要的函數就是 cv2.getPerspectiveTransform(rect, dst) 和 cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    M = cv.getPerspectiveTransform(rect, dst)
    warped = cv.warpPerspective(img, M, (maxWidth, maxHeight))
    return warped
 
 
def order_points(points):
    res = np.zeros((4, 2), dtype='float32')
    # 按照從前往後0，1，2，3分別表示左上、右上、右下、左下的順序將points中的數填入res中
 
    # 將四個坐標x與y相加，和最大的那個是右下角的坐標，最小的那個是左上角的坐標
    sum_hang = points.sum(axis=1)
    res[0] = points[np.argmin(sum_hang)]
    res[2] = points[np.argmax(sum_hang)]
 
    # 計算坐標x與y的離散插值np.diff()
    diff = np.diff(points, axis=1)
    res[1] = points[np.argmin(diff)]
    res[3] = points[np.argmax(diff)]
 
    # 返回result
    return res

輪廓識別——識別出選項

# 輪廓識別——識別出選項
thresh = cv.threshold(warped, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU)[1]
cvshow('thresh', thresh)
thresh_cnts, _ = cv.findContours(thresh, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
w_copy = warped.copy()
cv.drawContours(w_copy, thresh_cnts, -1, (0, 0, 255), 2)
cvshow('warped_contours', w_copy)
 
questionCnts = []
# 遍歷，挑出選項的cnts
for c in thresh_cnts:
    (x, y, w, h) = cv.boundingRect(c)
    ar = w / float(h)
    # 根據實際情況指定標準
    if w >= 20 and h >= 20 and ar >= 0.9 and ar <= 1.1:
        questionCnts.append(c)
 
# 檢查是否挑出瞭選項
w_copy2 = warped.copy()
cv.drawContours(w_copy2, questionCnts, -1, (0, 0, 255), 2)
cvshow('questionCnts', w_copy2)

成功將無關輪廓剔除

檢測每一行選擇的是哪一項，並將結果儲存起來，記錄正確的個數

# 檢測每一行選擇的是哪一項，並將結果儲存在元組bubble中，記錄正確的個數correct
# 按照從上到下t2b對輪廓進行排序
questionCnts = sort_contours(questionCnts, method="t2b")[0]
correct = 0
# 每行有5個選項
for (i, q) in enumerate(np.arange(0, len(questionCnts), 5)):
    # 排序
    cnts = sort_contours(questionCnts[q:q+5])[0]
 
    bubble = None
    # 得到每一個選項的mask並填充，與正確答案進行按位與操作獲得重合點數
    for (j, c) in enumerate(cnts):
        mask = np.zeros(thresh.shape, dtype='uint8')
        cv.drawContours(mask, [c], -1, 255, -1)
        # cvshow('mask', mask)
 
        # 通過按位與操作得到thresh與mask重合部分的像素數量
        bitand = cv.bitwise_and(thresh, thresh, mask=mask)
        totalPixel = cv.countNonZero(bitand)
 
        if bubble is None or bubble[0] < totalPixel:
            bubble = (totalPixel, j)
 
    k = bubble[1]
    color = (0, 0, 255)
    if k == right_key[i]:
        correct += 1
        color = (0, 255, 0)
 
    # 繪圖
    cv.drawContours(warped, [cnts[right_key[i]]], -1, color, 3)
    cvshow('final', warped)
def sort_contours(contours, method="l2r"):
    # 用於給輪廓排序，l2r, r2l, t2b, b2t
    reverse = False
    i = 0
    if method == "r2l" or method == "b2t":
        reverse = True
    if method == "t2b" or method == "b2t":
        i = 1
 
    boundingBoxes = [cv.boundingRect(c) for c in contours]
    (contours, boundingBoxes) = zip(*sorted(zip(contours, boundingBoxes), key=lambda a: a[1][i], reverse=reverse))
    return contours, boundingBoxes

 

用透過mask的像素的個數來判斷考生選擇的是哪個選項

計算最終得分並在圖中標註

# 計算最終得分並在圖中標註
score = (correct / 5.0) * 100
print(f"Score: {score}%")
cv.putText(warped, f"Score: {score}%", (10, 30), cv.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
cv.imshow("Original", img)
cv.imshow("Exam", warped)
cv.waitKey(0)

完整代碼

import cv2 as cv
import numpy as np
 
 
def cvshow(name, img):
    cv.imshow(name, img)
    cv.waitKey(0)
    cv.destroyAllWindows()
 
def four_point_transform(img, four_points):
    rect = order_points(four_points)
    (tl, tr, br, bl) = rect
 
    # 計算輸入的w和h的值
    widthA = np.sqrt((tr[0] - tl[0]) ** 2 + (tr[1] - tl[1]) ** 2)
    widthB = np.sqrt((br[0] - bl[0]) ** 2 + (br[1] - bl[1]) ** 2)
    maxWidth = max(int(widthA), int(widthB))
 
    heightA = np.sqrt((tl[0] - bl[0]) ** 2 + (tl[1] - bl[1]) ** 2)
    heightB = np.sqrt((tr[0] - br[0]) ** 2 + (tr[1] - br[1]) ** 2)
    maxHeight = max(int(heightA), int(heightB))
 
    # 變換後對應的坐標位置
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype='float32')
 
    # 最主要的函數就是 cv2.getPerspectiveTransform(rect, dst) 和 cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    M = cv.getPerspectiveTransform(rect, dst)
    warped = cv.warpPerspective(img, M, (maxWidth, maxHeight))
    return warped
 
 
def order_points(points):
    res = np.zeros((4, 2), dtype='float32')
    # 按照從前往後0，1，2，3分別表示左上、右上、右下、左下的順序將points中的數填入res中
 
    # 將四個坐標x與y相加，和最大的那個是右下角的坐標，最小的那個是左上角的坐標
    sum_hang = points.sum(axis=1)
    res[0] = points[np.argmin(sum_hang)]
    res[2] = points[np.argmax(sum_hang)]
 
    # 計算坐標x與y的離散插值np.diff()
    diff = np.diff(points, axis=1)
    res[1] = points[np.argmin(diff)]
    res[3] = points[np.argmax(diff)]
 
    # 返回result
    return res
 
 
def sort_contours(contours, method="l2r"):
    # 用於給輪廓排序，l2r, r2l, t2b, b2t
    reverse = False
    i = 0
    if method == "r2l" or method == "b2t":
        reverse = True
    if method == "t2b" or method == "b2t":
        i = 1
 
    boundingBoxes = [cv.boundingRect(c) for c in contours]
    (contours, boundingBoxes) = zip(*sorted(zip(contours, boundingBoxes), key=lambda a: a[1][i], reverse=reverse))
    return contours, boundingBoxes
 
# 正確答案
right_key = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}
 
# 輸入圖像
img = cv.imread('./images/test_01.jpg')
img_copy = img.copy()
img_gray = cv.cvtColor(img, cv.COLOR_BGR2GRAY)
cvshow('img-gray', img_gray)
 
# 圖像預處理
# 高斯降噪
img_gaussian = cv.GaussianBlur(img_gray, (5, 5), 1)
cvshow('gaussianblur', img_gaussian)
# canny邊緣檢測
img_canny = cv.Canny(img_gaussian, 80, 150)
cvshow('canny', img_canny)
 
# 輪廓識別——答題卡邊緣識別
cnts, hierarchy = cv.findContours(img_canny, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
cv.drawContours(img_copy, cnts, -1, (0, 0, 255), 3)
cvshow('contours-show', img_copy)
 
docCnt = None
 
# 確保檢測到瞭
if len(cnts) > 0:
    # 根據輪廓大小進行排序
    cnts = sorted(cnts, key=cv.contourArea, reverse=True)
 
    # 遍歷每一個輪廓
    for c in cnts:
        # 近似
        peri = cv.arcLength(c, True)  # arclength 計算一段曲線的長度或者閉合曲線的周長；
        # 第一個參數輸入一個二維向量，第二個參數表示計算曲線是否閉合
 
        approx = cv.approxPolyDP(c, 0.02 * peri, True)
        # 用一條頂點較少的曲線/多邊形來近似曲線/多邊形，以使它們之間的距離<=指定的精度；
        # c是需要近似的曲線，0.02*peri是精度的最大值，True表示曲線是閉合的
 
        # 準備做透視變換
        if len(approx) == 4:
            docCnt = approx
            break
 
 
# 透視變換——提取答題卡主體
docCnt = docCnt.reshape(4, 2)
warped = four_point_transform(img_gray, docCnt)
cvshow('warped', warped)
 
 
# 輪廓識別——識別出選項
thresh = cv.threshold(warped, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU)[1]
cvshow('thresh', thresh)
thresh_cnts, _ = cv.findContours(thresh, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
w_copy = warped.copy()
cv.drawContours(w_copy, thresh_cnts, -1, (0, 0, 255), 2)
cvshow('warped_contours', w_copy)
 
questionCnts = []
# 遍歷，挑出選項的cnts
for c in thresh_cnts:
    (x, y, w, h) = cv.boundingRect(c)
    ar = w / float(h)
    # 根據實際情況指定標準
    if w >= 20 and h >= 20 and ar >= 0.9 and ar <= 1.1:
        questionCnts.append(c)
 
# 檢查是否挑出瞭選項
w_copy2 = warped.copy()
cv.drawContours(w_copy2, questionCnts, -1, (0, 0, 255), 2)
cvshow('questionCnts', w_copy2)
 
 
# 檢測每一行選擇的是哪一項，並將結果儲存在元組bubble中，記錄正確的個數correct
# 按照從上到下t2b對輪廓進行排序
questionCnts = sort_contours(questionCnts, method="t2b")[0]
correct = 0
# 每行有5個選項
for (i, q) in enumerate(np.arange(0, len(questionCnts), 5)):
    # 排序
    cnts = sort_contours(questionCnts[q:q+5])[0]
 
    bubble = None
    # 得到每一個選項的mask並填充，與正確答案進行按位與操作獲得重合點數
    for (j, c) in enumerate(cnts):
        mask = np.zeros(thresh.shape, dtype='uint8')
        cv.drawContours(mask, [c], -1, 255, -1)
        cvshow('mask', mask)
 
        # 通過按位與操作得到thresh與mask重合部分的像素數量
        bitand = cv.bitwise_and(thresh, thresh, mask=mask)
        totalPixel = cv.countNonZero(bitand)
 
        if bubble is None or bubble[0] < totalPixel:
            bubble = (totalPixel, j)
 
    k = bubble[1]
    color = (0, 0, 255)
    if k == right_key[i]:
        correct += 1
        color = (0, 255, 0)
 
    # 繪圖
    cv.drawContours(warped, [cnts[right_key[i]]], -1, color, 3)
    cvshow('final', warped)
 
 
# 計算最終得分並在圖中標註
score = (correct / 5.0) * 100
print(f"Score: {score}%")
cv.putText(warped, f"Score: {score}%", (10, 30), cv.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
cv.imshow("Original", img)
cv.imshow("Exam", warped)
cv.waitKey(0)

到此這篇關於使用 OpenCV-Python 識別答題卡判卷的文章就介紹到這瞭,更多相關OpenCV Python 識別答題卡判卷內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet！

推薦閱讀：