sml2h3/ddddocr

pip install ddddocr

git clone https://github.com/sml2h3/ddddocr.git
cd ddddocr
pip install .

pip install ".[api]"

ddddocr.DdddOcr(
    ocr=True,           # 是否启用OCR功能
    det=False,          # 是否启用目标检测功能
    old=False,          # 是否使用旧版OCR模型
    beta=False,         # 是否使用Beta版OCR模型（新模型）
    use_gpu=False,      # 是否使用GPU加速
    device_id=0,        # 使用的GPU设备ID
    show_ad=True,       # 是否显示广告信息
    import_onnx_path="", # 自定义模型路径
    charsets_path="",    # 自定义字符集路径
    max_image_bytes=None, # 单图最大字节数（默认 8MB）
    max_image_side=None   # 单图最长边限制（默认 4096px）
)

import ddddocr

# 初始化OCR对象
ocr = ddddocr.DdddOcr()

# 读取图片
with open("验证码图片.jpg", "rb") as f:
    image = f.read()

# 识别图片
result = ocr.classification(image)
print(result)  # 输出识别结果

# 使用第二套OCR模型
ocr = ddddocr.DdddOcr(beta=True)

result = ocr.classification(image, png_fix=True)

import ddddocr

ocr = ddddocr.DdddOcr()
image = open("test.jpg", "rb").read()

# 获取识别结果的概率分布
result = ocr.classification(image, probability=True)

# 处理概率结果
s = ""
for i in result['probability']:
    s += result['charsets'][i.index(max(i))]

print(s)

# 概率输出结果示例
{
    'charsets': ['', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', ...],
    'probability': [
        [0.01, 0.02, 0.01, 0.03, 0.02, 0.01, 0.02, 0.75, 0.03, 0.05, 0.01, ...],  # 第一个字符的概率分布
        [0.01, 0.01, 0.02, 0.01, 0.03, 0.02, 0.01, 0.02, 0.01, 0.80, 0.01, ...],  # 第二个字符的概率分布
        ...
    ]
}

import ddddocr

ocr = ddddocr.DdddOcr()
image = open("test.jpg", "rb").read()

# 设置识别范围为数字
ocr.set_ranges(0)  # 等同于 ocr.set_ranges("0123456789")

# 或自定义字符范围
ocr.set_ranges("0123456789+-x/=")

result = ocr.classification(image)
print(result)

import ddddocr

ocr = ddddocr.DdddOcr()
image = open("test.jpg", "rb").read()

# 只保留红色和蓝色部分
result = ocr.classification(image, colors=["red", "blue"])
print(result)

# 自定义颜色范围
custom_ranges = {
    'light_blue': [(90, 30, 30), (110, 255, 255)]  # HSV颜色空间
}

result = ocr.classification(image, colors=["light_blue"], custom_color_ranges=custom_ranges)

import ddddocr
import cv2

# 初始化检测对象
det = ddddocr.DdddOcr(det=True, ocr=False)

# 读取图片
with open("test.jpg", 'rb') as f:
    image = f.read()

# 检测目标
bboxes = det.detection(image)
print(bboxes)  # 输出格式：[[x1, y1, x2, y2], ...]

# 可视化检测结果
im = cv2.imread("test.jpg")
for bbox in bboxes:
    x1, y1, x2, y2 = bbox
    im = cv2.rectangle(im, (x1, y1), (x2, y2), color=(0, 0, 255), thickness=2)
cv2.imwrite("result.jpg", im)

import ddddocr

# 初始化滑块检测对象
slide = ddddocr.DdddOcr(det=False, ocr=False)

# 读取滑块图和背景图
with open('target.png', 'rb') as f:
    target_bytes = f.read()

with open('background.png', 'rb') as f:
    background_bytes = f.read()

# 匹配位置
res = slide.slide_match(target_bytes, background_bytes)
print(f"滑块位置: {res}")

# 可视化结果
background = cv2.imdecode(np.frombuffer(background_bytes, np.uint8), cv2.IMREAD_COLOR)
x1, y1, x2, y2 = res["target"]

# 在背景图上绘制匹配位置
cv2.rectangle(background, (x1, y1), (x2, y2), (0, 255, 0), 2)

# 显示结果
plt.figure(figsize=(10, 6))
plt.imshow(cv2.cvtColor(background, cv2.COLOR_BGR2RGB))
plt.title("滑块匹配结果")
plt.axis('off')
plt.savefig("slide_result.jpg")
plt.show()

res = slide.slide_match(target_bytes, background_bytes, simple_target=True)

import ddddocr

slide = ddddocr.DdddOcr(det=False, ocr=False)

# 读取带有缺口阴影的图片和完整图片
with open('bg.jpg', 'rb') as f:
    target_bytes = f.read()

with open('fullpage.jpg', 'rb') as f:
    background_bytes = f.read()

# 比较差异
res = slide.slide_comparison(target_bytes, background_bytes)
print(res)  # 输出格式：{"target": [x, y]}

import ddddocr

# 导入自定义模型
ocr = ddddocr.DdddOcr(
    det=False, 
    ocr=False, 
    import_onnx_path="mymodel.onnx", 
    charsets_path="charsets.json"
)

with open('test.jpg', 'rb') as f:
    image_bytes = f.read()

res = ocr.classification(image_bytes)
print(res)

import ddddocr
import os
import time

# 初始化OCR对象（只需一次）
ocr = ddddocr.DdddOcr()

# 批量处理目录中的所有图片
def batch_process(directory):
    results = {}
    
    start_time = time.time()
    for filename in os.listdir(directory):
        if filename.endswith(('.png', '.jpg', '.jpeg', '.bmp')):
            file_path = os.path.join(directory, filename)
            
            with open(file_path, 'rb') as f:
                image = f.read()
                
            # 使用同一个OCR实例处理所有图片
            result = ocr.classification(image)
            results[filename] = result
    
    end_time = time.time()
    print(f"处理 {len(results)} 张图片耗时: {end_time - start_time:.2f} 秒")
    return results

# 使用示例
results = batch_process("./captchas/")
for filename, text in results.items():
    print(f"{filename}: {text}")

import ddddocr
import concurrent.futures
import os

def process_image(file_path):
    # 每个线程创建自己的OCR实例
    ocr = ddddocr.DdddOcr()
    
    with open(file_path, 'rb') as f:
        image = f.read()
    
    result = ocr.classification(image)
    return os.path.basename(file_path), result

def parallel_process(directory, max_workers=4):
    file_paths = [os.path.join(directory, f) for f in os.listdir(directory) 
                 if f.endswith(('.png', '.jpg', '.jpeg', '.bmp'))]
    
    results = {}
    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
        future_to_file = {executor.submit(process_image, file_path): file_path for file_path in file_paths}
        
        for future in concurrent.futures.as_completed(future_to_file):
            filename, result = future.result()
            results[filename] = result
    
    return results

# 使用示例
results = parallel_process("./captchas/", max_workers=8)

import ddddocr
import cv2
import numpy as np
from PIL import Image
import io

def preprocess_captcha(image_bytes):
    # 转换为OpenCV格式
    nparr = np.frombuffer(image_bytes, np.uint8)
    img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
    
    # 灰度化
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    
    # 二值化
    _, binary = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)
    
    # 去除小噪点
    kernel = np.ones((2, 2), np.uint8)
    opening = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel)
    
    # 转回字节流
    is_success, buffer = cv2.imencode(".jpg", opening)
    processed_bytes = io.BytesIO(buffer).getvalue()
    
    return processed_bytes

# 使用示例
ocr = ddddocr.DdddOcr()

with open("noisy_captcha.jpg", "rb") as f:
    image_bytes = f.read()

# 预处理验证码
processed_bytes = preprocess_captcha(image_bytes)

# 识别处理后的图片
result = ocr.classification(processed_bytes)
print(f"验证码识别结果: {result}")

import ddddocr
import cv2
import numpy as np
from PIL import Image
import io

# 初始化OCR对象
ocr = ddddocr.DdddOcr()

# 读取验证码图片
with open("captcha.jpg", "rb") as f:
    image_bytes = f.read()

# 转换为OpenCV格式进行预处理
# img = cv2.imdecode(np.frombuffer(image_bytes, np.uint8), cv2.IMREAD_COLOR)

# 预处理：灰度化、二值化等
# gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# _, binary = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY_INV)

# 转回字节流
# is_success, buffer = cv2.imencode(".jpg", binary)
# processed_bytes = io.BytesIO(buffer).getvalue()

# 识别处理后的图片
result = ocr.classification(image_bytes)
print(f"验证码识别结果: {result}")

import ddddocr
import cv2
import numpy as np
import matplotlib.pyplot as plt

# 初始化滑块检测对象
slide = ddddocr.DdddOcr(det=False, ocr=False)

# 读取滑块图和背景图
with open('target.png', 'rb') as f:
    target_bytes = f.read()

with open('background.png', 'rb') as f:
    background_bytes = f.read()

# 匹配位置
res = slide.slide_match(target_bytes, background_bytes)
print(f"滑块位置: {res}")

# 可视化结果
background = cv2.imdecode(np.frombuffer(background_bytes, np.uint8), cv2.IMREAD_COLOR)
x1, y1, x2, y2 = res["target"]

# 在背景图上绘制匹配位置
cv2.rectangle(background, (x1, y1), (x2, y2), (0, 255, 0), 2)

# 显示结果
plt.figure(figsize=(10, 6))
plt.imshow(cv2.cvtColor(background, cv2.COLOR_BGR2RGB))
plt.title("滑块匹配结果")
plt.axis('off')
plt.savefig("slide_result.jpg")
plt.show()

# 使用默认配置启动 API 服务
python -m ddddocr api

# 指定 API 服务配置
python -m ddddocr api --host 0.0.0.0 --port 8000 --workers 4

# 配置 OCR 功能
python -m ddddocr api --ocr true --beta true

# 配置目标检测功能
python -m ddddocr api --ocr false --det true

# 构建 Docker 镜像
docker build -t ddddocr-api .

# 运行 Docker 容器
docker run -d --name ddddocr-api -p 8000:8000 ddddocr-api

# 使用自定义配置运行
docker run -d --name ddddocr-api \
  -p 8000:8000 \
  -e DDDDOCR_OCR=true \
  -e DDDDOCR_BETA=true \
  -e DDDDOCR_WORKERS=4 \
  ddddocr-api

# 使用默认配置启动
docker-compose up -d

# 使用自定义配置启动
DDDDOCR_OCR=true DDDDOCR_BETA=true DDDDOCR_WORKERS=4 docker-compose up -d

POST /ocr

{
  "image": "图片的Base64编码字符串",
  "probability": false,
  "colors": [],
  "custom_color_ranges": null
}

{
  "result": "识别到的文字",
  "processing_time": 0.123
}

POST /det

{
  "image": "图片的Base64编码字符串"
}

{
  "result": [
    [x1, y1, x2, y2],
    ...
  ],
  "processing_time": 0.123
}

POST /slide_match

{
  "target_image": "目标图片的Base64编码字符串",
  "background_image": "背景图片的Base64编码字符串",
  "simple_target": false,
  "flag": false
}

{
  "result": {
    "target_x": 0,
    "target_y": 0,
    "target": [x1, y1, x2, y2]
  },
  "processing_time": 0.123
}

POST /slide_comparison

{
  "target_image": "目标图片的Base64编码字符串",
  "background_image": "背景图片的Base64编码字符串"
}

{
  "result": {
    "target": [x, y]
  },
  "processing_time": 0.123
}

POST /set_charset_range

{
  "charset_range": ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"]
}

{
  "result": "字符范围设置成功",
  "charset_range": ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"],
  "processing_time": 0.123
}

GET /health

{
  "status": "ok",
  "timestamp": 1628765432.1234
}

POST /ocr/file

import requests
import base64

# 读取图片文件并Base64编码
with open("captcha.png", "rb") as f:
    img_base64 = base64.b64encode(f.read()).decode()

# 发送OCR请求
url = "http://localhost:8000/ocr"
response = requests.post(url, json={"image": img_base64})

# 处理响应
result = response.json()
print(f"识别结果: {result['result']}")

import requests

# 准备文件
files = {"file": open("captcha.png", "rb")}

# 发送OCR请求
url = "http://localhost:8000/ocr/file"
response = requests.post(url, files=files)

# 处理响应
result = response.json()
print(f"识别结果: {result['result']}")