python - 在 Python OpenCV 中改进气泡表分级机的边缘检测
问题描述
我正在尝试创建一个气泡表扫描仪,但不幸的是,如果气泡表图片是由手机捕获的,它不会检测到图像,可能是由于阈值和边缘检测,或者由于图片的分辨率,不幸的是我有解决这个问题几乎没有进展。任何有关如何解决此问题的帮助或提示将不胜感激,
这是代码
from imutils.perspective import four_point_transform
from imutils import contours
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())
ANSWER_KEY = {0: 1, 1: 4, 2: 0, 3: 3, 4: 1}
# load the image, convert it to grayscale, blur it
# slightly, then find edges
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(blurred, 75, 200)
# find contours in the edge map, then initialize
# the contour that corresponds to the document
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
docCnt = None
# ensure that at least one contour was found
if len(cnts) > 0:
# sort the contours according to their size in
# descending order
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
# loop over the sorted contours
for c in cnts:
# approximate the contour
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
# if our approximated contour has four points,
# then we can assume we have found the paper
if len(approx) == 4:
docCnt = approx
break
# apply a four point perspective transform to both the
# original image and grayscale image to obtain a top-down
# birds eye view of the paper
paper = four_point_transform(image, docCnt.reshape(4, 2))
warped = four_point_transform(gray, docCnt.reshape(4, 2))
# apply Otsu's thresholding method to binarize the warped
# piece of paper
thresh = cv2.threshold(warped, 0, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
# find contours in the thresholded image, then initialize
# the list of contours that correspond to questions
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
questionCnts = []
# loop over the contours
for c in cnts:
# compute the bounding box of the contour, then use the
# bounding box to derive the aspect ratio
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h)
# in order to label the contour as a question, region
# should be sufficiently wide, sufficiently tall, and
# have an aspect ratio approximately equal to 1
if w >= 20 and h >= 20 and ar >= 0.9 and ar <= 1.1:
questionCnts.append(c)
# sort the question contours top-to-bottom, then initialize
# the total number of correct answers
questionCnts = contours.sort_contours(questionCnts,
method="top-to-bottom")[0]
correct = 0
# each question has 5 possible answers, to loop over the
# question in batches of 5
for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
# sort the contours for the current question from
# left to right, then initialize the index of the
# bubbled answer
cnts = contours.sort_contours(questionCnts[i:i + 5])[0]
bubbled = None
# loop over the sorted contours
for (j, c) in enumerate(cnts):
# construct a mask that reveals only the current
# "bubble" for the question
mask = np.zeros(thresh.shape, dtype="uint8")
cv2.drawContours(mask, [c], -1, 255, -1)
# apply the mask to the thresholded image, then
# count the number of non-zero pixels in the
# bubble area
mask = cv2.bitwise_and(thresh, thresh, mask=mask)
total = cv2.countNonZero(mask)
# if the current total has a larger number of total
# non-zero pixels, then we are examining the currently
# bubbled-in answer
if bubbled is None or total > bubbled[0]:
bubbled = (total, j)
# initialize the contour color and the index of the
# *correct* answer
color = (0, 0, 255)
k = ANSWER_KEY[q]
# check to see if the bubbled answer is correct
if k == bubbled[1]:
color = (0, 255, 0)
correct += 1
# draw the outline of the correct answer on the test
cv2.drawContours(paper, [cnts[k]], -1, color, 3)
# grab the test taker
score = (correct / 5.0) * 100
print("[INFO] score: {:.2f}%".format(score))
cv2.putText(paper, "{:.2f}%".format(score), (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
cv2.imshow("Original", image)
cv2.imshow("Exam", paper)
cv2.waitKey(0)
解决方案
推荐阅读
- reactjs - 我无法在 REACT 中使用 Material UI 构建此布局
- graph-theory - Dijkstra 和负权重 - 计算错误的距离重要吗?
- mongodb - $unset 规范必须是字符串或数组
- hyperledger-fabric-sdk-go - 我正在学习fabric-sdk-go。当我执行“make run”来运行我的应用程序时,有两个 WARN。这意味着什么剂量?
- r - 如何在自定义函数中使用响应式?
- python - 404 未找到 ngrok、FastApi 和 uvicorn
- python - 如何在 Pytorch 中为 Seq2seq 模型实现小批量下降
- bash - 更改单列中的日期格式
- javascript - 加载图像后运行另一个函数
- tailwind-css - 内容溢出时的 Tailwind CSS 水平滚动