pip install paddleocr labelme opencv-python

import os
import cv2
from paddleocr import PaddleOCR
def auto_label_image(image_path, output_path):
    # 檢查文件是否存在
    if not os.path.exists(image_path):
        print(f"Error: File not found: {image_path}")
        return
    # 加載圖像
    image = cv2.imread(image_path)
    if image is None:
        print(f"Error: Failed to load image. Check the file path or format: {image_path}")
        return
    # 圖像預(yù)處理
    gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    _, binary_image = cv2.threshold(gray_image, 128, 255, cv2.THRESH_BINARY)
    # 保存預(yù)處理后的圖片（可選，用于調(diào)試）
    preprocessed_path = os.path.join(output_path, "processed_image.jpg")
    cv2.imwrite(preprocessed_path, binary_image)
    # 初始化 OCR
    ocr = PaddleOCR(use_angle_cls=True, lang='en')
    # OCR 識(shí)別
    results = ocr.ocr(preprocessed_path)
    if not results or not results[0]:
        print(f"No text detected in the image: {image_path}")
        return
    # 獲取圖像尺寸
    image_height, image_width, _ = image.shape
    # 構(gòu)建標(biāo)注 JSON
    label_data = {
        "version": "4.5.7",
        "flags": {},
        "shapes": [],
        "imagePath": os.path.basename(image_path),
        "imageData": None,
        "imageHeight": image_height,
        "imageWidth": image_width,
    }
    # 遍歷 OCR 結(jié)果
    for line in results[0]:
        points = line[0]  # 字符位置 [左上, 右上, 右下, 左下]
        text = line[1][0]  # 識(shí)別的文本
        shape = {
            "label": text,
            "points": [points[0], points[2]],  # 左上角和右下角
            "group_id": None,
            "shape_type": "rectangle",
            "flags": {}
        }
        label_data["shapes"].append(shape)
    # 保存標(biāo)注 JSON
    json_path = os.path.join(output_path, os.path.basename(image_path).replace('.jpg', '.json'))
    with open(json_path, 'w') as f:
        import json
        json.dump(label_data, f, indent=4)
    print(f"Saved LabelMe annotation: {json_path}")
# 示例
image_path = r"C:\Users\wangzq\Desktop\images\captcha.jpg"
output_path = "./annotations"
os.makedirs(output_path, exist_ok=True)
auto_label_image(image_path, output_path)

gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
_, binary_image = cv2.threshold(gray_image, 128, 255, cv2.THRESH_BINARY)

ocr = PaddleOCR(use_angle_cls=True, lang='en')
results = ocr.ocr(preprocessed_path)

for image_file in os.listdir(input_folder):
    image_path = os.path.join(input_folder, image_file)
    auto_label_image(image_path, output_path)

{
    "version": "4.5.7",
    "flags": {},
    "shapes": [
        {
            "label": "OZLQ",
            "points": [
                [
                    6.0,
                    1.0
                ],
                [
                    68.0,
                    21.0
                ]
            ],
            "group_id": null,
            "shape_type": "rectangle",
            "flags": {}
        }
    ],
    "imagePath": "captcha.png",
    "imageData": null,
    "imageHeight": 22,
    "imageWidth": 76
}

{
    "version": "4.5.7",
    "flags": {},
    "shapes": [
        {
            "label": "3081",
            "points": [
                [
                    6.0,
                    1.0
                ],
                [
                    63.0,
                    21.0
                ]
            ],
            "group_id": null,
            "shape_type": "rectangle",
            "flags": {}
        }
    ],
    "imagePath": "captcha.png",
    "imageData": null,
    "imageHeight": 22,
    "imageWidth": 76
}