隨著現代圖像處理和人工智能技術的快速發展，不少學者嘗試講CV應用到教學領域，能夠代替老師去閱卷，將老師從繁雜勞累的閱卷中解放出來，從而進一步有效的推動教學質量上一個臺階。

傳統的人工閱卷，工作繁瑣，效率低下，進度難以控制且容易出現試卷遺漏未改、登分失誤等現象。

現代的“機器閱卷”，工作便捷、效率高、易操作，只需要一個相機（手機），拍照即可獲取成績，可以導入Excel表格便于存檔管理。

下面我們從代碼實現的角度來解釋一下我們這個簡易答題卡識別系統的工作原理。
第一步，導入工具包及一系列的預處理

import numpy as np
import argparse
import imutils
import cv2
# 設置參數
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", defaul)
args = vars(ap.parse_args())
# 正確答案
ANSWER_KEY = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1} #
def order_points(pts):
   # 一共4個坐標點
   rect = np.zeros((4, 2), dtype = "float32")

   # 按順序找到對應坐標0,1,2,3分別是 左上，右上，右下，左下
   # 計算左上，右下
   s = pts.sum(axis = 1)
   rect[0] = pts[np.argmin(s)]
   rect[2] = pts[np.argmax(s)]
   # 計算右上和左下
   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):
   # 獲取輸入坐標點
   rect = order_points(pts)
   (tl, tr, br, bl) = rect
   # 計算輸入的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))
   # 變換后對應坐標位置
   dst = np.array([
      [0, 0],
      [maxWidth - 1, 0],
      [maxWidth - 1, maxHeight - 1],
      [0, maxHeight - 1]], dtype = "float32")
   # 計算變換矩陣
   M = cv2.getPerspectiveTransform(rect, dst)
   warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
   return warped # 返回變換后結果

def sort_contours(cnts, metho):
    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()  


image = cv2.imread(args["image"])
contours_img = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(blurred, 75, 200)
# 輪廓檢測
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
   cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(contours_img,cnts,-1,(0,0,255),3) 
docCnt = None

# 確保檢測到了
if len(cnts) > 0:
   # 根據輪廓大小進行排序
   cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
   for c in cnts:   # 遍歷每一個輪廓
      # 近似
      peri = cv2.arcLength(c, True)
      approx = cv2.approxPolyDP(c, 0.02 * peri, True)
      # 準備做透視變換
      if len(approx) == 4:
         docCnt = approx
         break
# 執行透視變換
warped = four_point_transform(gray, docCnt.reshape(4, 2))

thresh = cv2.threshold(warped, 0, 255,
   cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1] 
thresh_Contours = thresh.copy()
# 找到每一個圓圈輪廓
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
   cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(thresh_Contours,cnts,-1,(0,0,255),3) 
questionCnts = []
for c in cnts:# 遍歷
   # 計算比例和大小
   (x, y, w, h) = cv2.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)
# 按照從上到下進行排序
questionCnts = sort_contours(questionCnts,
   metho)[0]
correct = 0
# 每排有5個選項
for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
   cnts = sort_contours(questionCnts[i:i + 5])[0]
   bubbled = None
   for (j, c) in enumerate(cnts):  # 遍歷每一個結果
      # 使用mask來判斷結果
      mask = np.zeros(thresh.shape, dtyp)
      cv2.drawContours(mask, [c], -1, 255, -1) #-1表示填充
      # 通過計算非零點數量來算是否選擇這個答案
      mask = cv2.bitwise_and(thresh, thresh, mask=mask)
      total = cv2.countNonZero(mask)
      # 通過閾值判斷
      if bubbled is None or total > bubbled[0]:
         bubbled = (total, j)
   # 第二步，與正確答案進行對比
   color = (0, 0, 255)
   k = ANSWER_KEY[q]
   # 判斷正確
   if k == bubbled[1]:
      color = (0, 255, 0)
      correct += 1
   cv2.drawContours(warped, [cnts[k]], -1, color, 3) #繪圖

   #正確率的文本顯示
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("Input", image)
cv2.imshow("Output", warped)
cv2.waitKey(0)

本文由博客一文多發平臺 OpenWrite 發布！

審核編輯 黃昊宇