【从小项目学图片处理】#1 答题卡识别

说明：项目皆参考于网上，代码也有大部分参考原文。仅用于学习和练习图像处理操作。
项目原文： Bubble sheet multiple choice scanner and test grader using OMR, Python and OpenCV

问题描述：
给定下面一张答题卡，识别并依次输出被涂黑的字母 BEACB。

解决思路/步骤：

• 1# 识别图像中答题卡部分，通过透视变换，将图像摆正。
• 2# 识别并提取答题卡中圆形部分。
• 3# 判断被涂黑的部分，输出被涂黑的字母。

代码实现:

• 用c++实现

#include <opencv2/opencv.hpp>
#include <iostream>
using namespace cv;
using namespace std;

bool cmp1(Rect a, Rect b){
	return (a.y<=b.y);
}
bool cmp2(Rect a, Rect b){
	return (a.x<=b.x);
}

int main(int argc, char** argv){
	if(argc==1) {
		cout << "Usage: ProgramName PicturnFile" << endl;
		return -1;
	}
	Mat imgSrc = imread(argv[1]);	
	if(imgSrc.empty()) {
		cout << "Failed to load image!" << endl;
		return -1;
	}

	Mat img = Mat::zeros(imgSrc.size(),imgSrc.type());
	cvtColor(imgSrc, img, COLOR_BGR2GRAY);
	Mat gray = img.clone();
	GaussianBlur(img, img, Size(5,5), 0);
	Canny(img, img, 75, 200);

	vector<vector<Point>> contours;
	vector<Vec4i> hierarchy;
	findContours(img, contours, hierarchy, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE);

//	Mat test = Mat::zeros(img.size(), img.type());
//	drawContours(test, contours, -1, Scalar(255), 2);
	int k = 0;
	float area = 0;
	for(int i=0; i<contours.size(); i++){
		float Area = contourArea(contours[i]);
		if(area <= Area) {
			area = Area;
			k = i;
		}
	}
	
	vector<Point2f> p;
	double len;
	len = arcLength(contours[k], true);
	approxPolyDP(contours[k], p, len * 0.02, true);
	
	int height = max((int)sqrt((p[0].y-p[1].y)*(p[0].y-p[1].y)),(int)sqrt((p[2].y-p[3].y)*(p[2].y-p[3].y)));
	int width = max((int)sqrt((p[0].x-p[3].x)*(p[0].x-p[3].x)),(int)sqrt((p[2].x-p[1].x)*(p[2].x-p[1].x)));
	
	vector<Point2f> pdst = {Point2f(0,0), Point2f(0,width-1), Point2f(height-1,width-1), Point2f(height-1,0)};

	Mat m(3, 3, CV_32F);
	m = getPerspectiveTransform(p, pdst);
	warpPerspective(gray, img, m, Size(height, width));

	threshold(img, img, 0, 255, THRESH_BINARY_INV | THRESH_OTSU);
	contours.clear();
	findContours(img, contours, hierarchy, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE);

	vector<Rect> rec;
	for(int i=0; i<contours.size(); i++){
		Rect rect = boundingRect(contours[i]);
		float ar = rect.width/(float)rect.height;
		if(rect.width >= 20 && rect.height >= 20 ){
			rec.push_back(rect);
		}
	}

	sort(rec.begin(), rec.end(), cmp1);
	for(vector<Rect>::iterator it=rec.begin(); it!=rec.end(); it+=5){
		sort(it, it+5, cmp2);
	}
	
	vector<int> ans(5,0);
	for(int i=0; i<5; i++){
		int maxcount = 0;
		for(int j=0; j<5; j++){
			Mat mask = Mat::zeros(img.size(),img.type());
			rectangle(mask, rec[i*5+j], Scalar(255), -1);
			bitwise_and(mask, img, mask);
			int count = countNonZero(mask);
			if(count >= maxcount){
				maxcount = count;
				ans[i] = j;	
			}
		}
	}
	imshow("img",img);
	waitKey(0);
	for(int i=0; i<ans.size(); i++){
		char out= 'A'+ans[i];
		cout << out;
	}

	return 0;
}

• 用python实现（源项目代码）

# import the necessary packages
from imutils.perspective import four_point_transform
from imutils import contours
import numpy as np
import argparse
import imutils
import cv2
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
	help="path to the input image")
args = vars(ap.parse_args())
# define the answer key which maps the question number
# to the correct answer
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)