我正在尝试将手写文本从 NIST 表单数据集中拆分为单独的行。这是数据集的链接: https ://www.nist.gov/srd/nist-special-database-19
我正在使用的代码基于 stackoverflow 上的一个类似问题,但由于某些字符接触,它并不能很好地工作。这是代码:
import cv2
import numpy as np
#import image
image = cv2.imread('form1.jpg')
#cv2.imshow('orig',image)
#cv2.waitKey(0)
#grayscale
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
cv2.imshow('gray',gray)
cv2.waitKey(0)
#binary
ret,thresh = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
cv2.imshow('second',thresh)
cv2.waitKey(0)
#dilation
kernel = np.ones((5,100), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
cv2.imshow('dilated',img_dilation)
cv2.waitKey(0)
#find contours
im2,ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
#sort contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
# Get bounding box
x, y, w, h = cv2.boundingRect(ctr)
# Getting ROI
roi = image[y:y+h, x:x+w]
# show ROI
cv2.imshow('segment no:'+str(i),roi)
cv2.rectangle(image,(x,y),( x + w, y + h ),(90,0,255),2)
cv2.waitKey(0)
cv2.imshow('marked areas',image)
cv2.waitKey(0)
即使某些字符重叠,我怎样才能让它正确分割线?