项目介绍:
需要识别出下面这个答题卡哪个选项被选择了:
# 预处理
image = cv2.imread(args["image"])
contours_img = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
cv_show('blurred',blurred)
edged = cv2.Canny(blurred, 75, 200)
cv_show('edged',edged)
读入图像,复制一下,进行灰度处理:
之后再进行边缘检测:
之后进行轮廓检测,检测完之后有三个值,我们只需要最外面的那个轮廓值就可以了。
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(contours_img,cnts,-1,(0,0,255),3)
cv_show('contours_img',contours_img)
docCnt = None
之后依据轮廓面积进行排序
# 确保检测到了
if len(cnts) > 0:
# 根据轮廓大小进行排序
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
# 遍历每一个轮廓
for c in cnts:
# 近似
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
# 准备做透视变换,如果多边形的顶点有四个
if len(approx) == 4:
docCnt = approx
break
之后我们执行透视变换:
def four_point_transform(image, pts):
# 获取输入坐标点
rect = order_points(pts)
(tl, tr, br, bl) = rect
# 计算输入的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))
# 变换后对应坐标位置
dst = np.array([
[0, 0],
[maxWidth - 1, 0],
[maxWidth - 1, maxHeight - 1],
[0, maxHeight - 1]], dtype = "float32")
# 计算变换矩阵
M = cv2.getPerspectiveTransform(rect, dst)
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
# 返回变换后结果
return warped
采用自适应的阈值对其进行处理:
# Otsu's 阈值处理
thresh = cv2.threshold(warped, 0, 255,
cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
cv_show('thresh',thresh)
之后再轮廓检测,检测圆:
# 找到每一个圆圈轮廓
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)[1]
cv2.drawContours(thresh_Contours,cnts,-1,(0,0,255),3)
cv_show('thresh_Contours',thresh_Contours)
依据实际情况,划定固定区域,然后进行圆检测,计算比例,将不符合的去除掉:
questionCnts = []
# 遍历
for c in cnts:
# 计算比例和大小
(x, y, w, h) = cv2.boundingRect(c)
ar = w / float(h)
# 根据实际情况指定标准
if w >= 20 and h >= 20 and ar >= 0.9 and ar <= 1.1:
questionCnts.append(c)
# 按照从上到下进行排序
questionCnts = sort_contours(questionCnts,
method="top-to-bottom")[0]
按y轴坐标对其进行排序
def sort_contours(cnts, method="left-to-right"):
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))
按照每排,也就是每道题目来对其进行选择:
# 每排有5个选项
for (q, i) in enumerate(np.arange(0, len(questionCnts), 5)):
# 排序
cnts = sort_contours(questionCnts[i:i + 5])[0]
bubbled = None
# 遍历每一个结果
for (j, c) in enumerate(cnts):
# 使用mask来判断结果
mask = np.zeros(thresh.shape, dtype="uint8")
cv2.drawContours(mask, [c], -1, 255, -1) #-1表示填充
cv_show('mask',mask)
# 通过计算非零点数量来算是否选择这个答案
mask = cv2.bitwise_and(thresh, thresh, mask=mask)
total = cv2.countNonZero(mask)
# 通过阈值判断
if bubbled is None or total > bubbled[0]:
bubbled = (total, j)
# 对比正确答案
color = (0, 0, 255)
k = ANSWER_KEY[q]
# 判断正确
if k == bubbled[1]:
color = (0, 255, 0)
correct += 1
# 绘图
cv2.drawContours(warped, [cnts[k]], -1, color, 3)
最终结果显示:
完整代码:https://github.com/ZhiqiangHo/Opencv-Computer-Vision-Practice-Python-
我的微信公众号名称:深度学习与先进智能决策
微信公众号ID:MultiAgent1024
公众号介绍:主要研究分享深度学习、机器博弈、强化学习等相关内容!期待您的关注,欢迎一起学习交流进步!