使用Python-OpenCV手寫以數字識別和提取

Question

我想按順序提取框內的數字。

原始圖像

我使用分水嶺算法來分隔連接到框的數字，但它不能正確地對數字進行輪廓，而是僅選擇數字的某些部分。

#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]

目前的結果

Answer 1

這是我的方法。 我會盡量詳細說明：

• 將圖像轉換為灰度
• 執行精確邊緣檢測
• 刪除水平和垂直線以隔離字符
• 執行形態操作以增強字母
• 查找輪廓
• 使用輪廓區域和縱橫比過濾輪廓
• 從左到右排序輪廓以按順序提取數字
• 迭代排序的輪廓並提取ROI

首先，我們使用cv2.Canny()執行Canny邊緣檢測

接下來的目標是刪除我們可以隔離數字的垂直和水平線。 我們首先創建各種內核，每個內核都以水平，垂直或一般方向為目標

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))

我們首先用cv2.erode()刪除水平線

現在我們用cv2.dilate()垂直線

接下來我們刪除垂直線

現在注意我們幾乎沒有剩下任何東西，所以我們必須通過擴張來恢復數字

從這里我們使用cv2.findContours()找到輪廓。 我們使用cv2.contourArea()和縱橫比進行過濾以獲得邊界框。

現在按順序提取數字，我們使用imutils.contours.sort_contours()

最后，我們提取每個數字的ROI並保存圖像。 這是按順序保存的ROI的屏幕截圖

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)