python识别图片文字

python识别图片文字

from PIL import Image
import pytesseract
import cv2
import numpy as np

src_path=""

def get_string(img_path):
	# 读取图片
	img = cv2.imread(img_path)
	# 转化为灰度图
	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)
	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_GANSSIAN_C, cv2.THRESH_BINARY, 11, 2)
	cv2.imwrite(src_path + "thres.png", img)
	
	result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))
	return result

print get_string(src_path + "1.png")