import cv2
import pytesseract
import base64
import numpy as np
# 从图片路径进行OCR识别
def ocr_from_path(image_path):
    # 读取图片
    image = cv2.imread(image_path, cv2.COLOR_BGR2GRAY)
    # 使用Tesseract进行OCR识别
    ocr_text = pytesseract.image_to_string(image, lang='chi_sim')#chi_sim ocrd
    return ocr_text

# 从Base64编码的图像进行OCR识别
def ocr_from_base64(base64_string):
    # 解码Base64编码的字符串为字节数据
    image_data = base64.b64decode(base64_string)
    # 将字节数据转换为OpenCV图像
    nparr = np.frombuffer(image_data, np.uint8)
    image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
    # 使用Tesseract进行OCR识别
    ocr_text = pytesseract.image_to_string(image, lang='chi_sim')
    return ocr_text


string = ocr_from_path("/Users/wangvivi/Desktop/Code/ocrtest/images/id_card.JPG")
print(f"{string}")