利用Python開發(fā)人工智能閱卷系統(tǒng)

隨著現(xiàn)代圖像處理和人工智能技術的快速發(fā)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(tǒng)的人工閱卷，工作繁瑣，效率低下，進度難以控制且容易出現(xiàn)試卷遺漏未改、登分失誤等現(xiàn)象。

現(xiàn)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(xiàn)的角度來解釋一下我們這個簡易答題卡識別系統(tǒng)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(shù)
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(jù)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(zhí)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(jù)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(shù)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(fā)平臺 OpenWrite 發(fā)布！

審核編輯 黃昊宇