挑战:使用python提取弯曲文本

pip install opencv-python pytesseract Pillow

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

# 如果在 Windows 上，设置 Tesseract 的路径
# pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

def preprocess_image(image_path):
    # 读取图像
    image = cv2.imread(image_path)

    # 转换为灰度图像
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # 应用高斯模糊
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)

    # 应用边缘检测
    edged = cv2.Canny(blurred, 50, 150)

    # 查找轮廓
    contours, _ = cv2.findContours(edged, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # 找到最大轮廓
    max_contour = max(contours, key=cv2.contourArea)

    # 创建掩膜
    mask = np.zeros_like(gray)
    cv2.drawContours(mask, [max_contour], -1, 255, -1)

    # 应用掩膜
    result = cv2.bitwise_and(gray, gray, mask=mask)

    return result

def extract_text(image):
    # 使用 Pytesseract 提取文本
    custom_config = r'--oem 3 --psm 6'  # 选择 OCR 引擎模式和页面分割模式
    text = pytesseract.image_to_string(image, config=custom_config)
    return text

if __name__ == '__main__':
    image_path = 'path/to/your/image.jpg'  # 替换为您的图像路径
    preprocessed_image = preprocess_image(image_path)
    extracted_text = extract_text(preprocessed_image)

    print("提取的文本:")
    print(extracted_text)