我正在尝试使用python cv2从图像中提取文本。结果很可悲,我想不出一种方法来改进我的代码。 我认为在提取文本之前需要对图像进行处理,但不确定如何处理。
我试图将其转换为黑白,但没有运气。
import cv2
import os
import pytesseract
from PIL import Image
import time
pytesseract.pytesseract.tesseract_cmd='C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
cam = cv2.VideoCapture(1,cv2.CAP_DSHOW)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, 8000)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT, 6000)
while True:
return_value,image = cam.read()
image=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
image = image[127:219, 508:722]
#(thresh, image) = cv2.threshold(image, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
cv2.imwrite('test.jpg',image)
print('Text detected: {}'.format(pytesseract.image_to_string(Image.open('test.jpg'))))
time.sleep(2)
cam.release()
#os.system('del test.jpg')
答案 0 :(得分:3)
在执行文本提取之前进行预处理以清洁图像会有所帮助。这是一种简单的方法
首先我们将其转换为灰度,然后使用sharpening kernel
来锐化图像接下来,我们自适应阈值以获取二进制图像
现在我们执行morphological transformations来平滑图像
最后我们将图像反转
import cv2
import numpy as np
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
sharpen_kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
sharpen = cv2.filter2D(gray, -1, sharpen_kernel)
thresh = cv2.threshold(sharpen, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=1)
result = 255 - close
cv2.imshow('sharpen', sharpen)
cv2.imshow('thresh', thresh)
cv2.imshow('close', close)
cv2.imshow('result', result)
cv2.waitKey()
答案 1 :(得分:0)
尝试一下
from PIL import image
import PIL.image
from pytesseract import image_to_string
import pytesseract
pytesseract.pytesseract.tesseract_cmd = '_________'
#tesseract executable path -- if not added to
environment path, if added ignore
Output =
pytesseract.image_to_string(PIL.image.open('image
wants to read'). convert ("RBG"), Lang='eng')
Print (output)