campus_activity_system/utils/ocr_utils.py

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

def extract_text_from_image(image_path):
    """从图片中提取文本"""
    # 使用OpenCV读取图像
    img = cv2.imread(image_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # 使用PIL将灰度图像转换为二值图像（黑白）
    _, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)

    # 使用pytesseract进行OCR
    text = pytesseract.image_to_string(thresh, lang='chi_sim')  # 支持中文
    return text.strip()

# 示例调用
if __name__ == "__main__":
    text = extract_text_from_image('path_to_image.png')
    print("Extracted Text:", text)