用Python-OpenCV手写按序数字识别与提取

Question

我想按顺序提取框中的数字。

原图

我使用分水岭算法来分隔连接到框的数字，但它不会正确地绘制数字轮廓，而是仅选择数字的某些部分。

#To get in big box that contain smaller boxes from the image
img = cv2.imread('1_6.png',0)
img = cv2.GaussianBlur(img,(3,3),1)
_,img  = cv2.threshold(img,240,255,cv2.THRESH_BINARY)
img = cv2.GaussianBlur(img,(11,11),1)
edges = cv2.Canny(img,100,200)
_,c,h = cv2.findContours(edges.copy(),cv2.RETR_CCOMP,cv2.CHAIN_APPROX_NONE)
img = cv2.imread('1_6.png')
temp_c = sorted(c,key=cv2.contourArea,reverse=True)

#Select the big box
epsilon = 0.0001*cv2.arcLength(temp_c[0],True)
approx = cv2.approxPolyDP(temp_c[0],epsilon,True)

#Crop big box
pts = approx.copy()
rect = cv2.boundingRect(pts)
x,y,w,h = rect
croped = img[y:y+h, x:x+w].copy()

## (2) make mask
pts = pts - pts.min(axis=0)

mask = np.ones(croped.shape[:2], np.uint8)
cv2.drawContours(mask, [pts], -1, (255, 255, 255), -1, cv2.LINE_AA)

## (3) do bit-op
dst = cv2.bitwise_and(croped, croped, mask=mask)


gray = cv2.cvtColor(dst,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
kernel = np.ones((1,1),np.uint8)
opening = cv2.morphologyEx(thresh,cv2.MORPH_CLOSE,kernel, iterations = 2)

sure_bg = cv2.dilate(opening,kernel,iterations=1)

dist_transform = cv2.distanceTransform(opening,cv2.DIST_L2,5)

ret, sure_fg = cv2.threshold(dist_transform,0.3*dist_transform.max(),255,0)

sure_fg = np.uint8(sure_fg)

unknown = cv2.subtract(sure_bg,sure_fg)

ret, markers = cv2.connectedComponents(sure_fg)

# Add one to all labels so that sure background is not 0, but 1
markers = markers+1

# Now, mark the region of unknown with zero
markers[unknown==255] = 0

plt.imshow(markers,cmap="gray")

img = dst.copy()
markers = cv2.watershed(dst,markers)
img[markers == -1] = [0,0,255]

当前结果

Answer 1

这是我的方法。我会尝试尽可能详细：

• 将图像转换为灰度
• 执行精明的边缘检测
• 删除水平线和垂直线以隔离字符
• 执行形态运算以增强字母
• 寻找轮廓
• 使用轮廓面积和纵横比过滤轮廓
• 从左到右对轮廓进行排序以按顺序提取数字
• 迭代排序轮廓并提取 ROI

首先我们使用 Canny 边缘检测cv2.Canny()

接下来的目标是删除垂直和水平线，我们可以隔离数字。我们首先创建各种内核，每个内核都针对水平、垂直或一般方向

vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,2))
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,1))
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (3,3))

我们首先删除水平线cv2.erode()

现在我们用以下方法扩大垂直线cv2.dilate()

接下来我们删除垂直线

现在请注意，我们几乎没有剩下任何内容，因此我们必须通过扩张来恢复数字

从这里我们使用 找到轮廓cv2.findContours()。我们使用cv2.contourArea()和 按纵横比进行过滤以获得边界框。

现在要按顺序提取数字，我们使用imutils.contours.sort_contours()

最后，我们提取每个数字的 ROI 并保存图像。这是按顺序保存的 ROI 的屏幕截图

import cv2
import numpy as np
from imutils import contours

image = cv2.imread('1.png')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
canny = cv2.Canny(gray, 130, 255, 1)

vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,2))
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,1))
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (3,3))
erode = cv2.erode(canny, vertical_kernel)
cv2.imshow('remove horizontal', erode)
dilate = cv2.dilate(erode, vertical_kernel, iterations=5)
cv2.imshow('dilate vertical', dilate)
erode = cv2.erode(dilate, horizontal_kernel, iterations=1)
cv2.imshow('remove vertical', erode)
dilate = cv2.dilate(erode, kernel, iterations=4)
cv2.imshow('dilate horizontal', dilate)

cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

digit_contours = []
for c in cnts:
    area = cv2.contourArea(c)
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.01 * peri, True)
    x,y,w,h = cv2.boundingRect(approx)
    aspect_ratio = w / float(h)

    if (aspect_ratio >= 0.4 and aspect_ratio <= 1.3):
        if area > 150:
            ROI = original[y:y+h, x:x+w]
            cv2.rectangle(image,(x,y),(x+w,y+h),(0,255,0),2)
            digit_contours.append(c)

sorted_digit_contours = contours.sort_contours(digit_contours, method='left-to-right')[0]
contour_number = 0
for c in sorted_digit_contours:
    x,y,w,h = cv2.boundingRect(c)
    ROI = original[y:y+h, x:x+w]
    cv2.imwrite('ROI_{}.png'.format(contour_number), ROI)
    contour_number += 1

cv2.imshow('canny', canny)
cv2.imshow('image', image)
cv2.waitKey(0)