我在 Python 中使用以下代码从图像中提取文本,
import cv2
import numpy as np
import pytesseract
from PIL import Image
# Path of working folder on Disk
src_path = "<dir path>"
def get_string(img_path):
# Read image with opencv
img = cv2.imread(img_path)
# Convert to gray
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)
# Write image after removed noise
cv2.imwrite(src_path + "removed_noise.png", img)
# Apply threshold to get image with only black and white
#img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2)
# Write the image after apply opencv to do some ...
cv2.imwrite(src_path + "thres.png", img)
# Recognize text with tesseract for python
result = pytesseract.image_to_string(Image.open(img_path))#src_path+ "thres.png"))
# Remove template file
#os.remove(temp)
return result
print '--- Start recognize text from image ---'
print get_string(src_path + "test.jpg")
print "------ Done -------"
但是输出不正确..输入文件是,
收到的输出是“0001”而不是“D001”
收到的输出是“3001”而不是“B001”
从图像中检索正确字符所需的代码更改是什么,以及训练 pytesseract 为图像中的所有字体类型返回正确的字符[包括粗体字符]