基于Node.js和Tesseract.js实现验证码识别服务

captcha-reader/
├── src/
│   ├── routes/
│   │   └── captcha.js       # 验证码识别路由
│   ├── services/
│   │   └── captchaService.js # 验证码识别服务
│   ├── utils/
│   │   └── imageUtils.js     # 图像处理工具
│   └── app.js                # 应用入口
├── package.json              # 项目配置和依赖
├── test-captcha-api.js       # API 测试脚本
└── test-captcha-data.json    # 测试数据

// src/services/captchaService.js 核心代码

/**
 * Recognize captcha image and calculate result
 * @param {string} base64Image - Base64 encoded captcha image
 * @returns {Promise<Object>} Recognition and calculation result
 */
exports.recognizeCaptcha = async (base64Image) => {
  try {
    // 解码 base64 图片
    const imageBuffer = await decodeBase64Image(base64Image);
    
    // 预处理图片
    const processedImage = await preprocessImage(imageBuffer);
    
    // 创建 Tesseract worker
    const worker = await createWorker('eng', 1, {
      logger: m => console.log('   Tesseract:', m)
    });
    
    try {
      // 配置 Tesseract 识别选项
      await worker.setParameters({
        tessedit_char_whitelist: '0123456789+-*/x=?',
        tessedit_pageseg_mode: 7, // 单行文本模式
        preserve_interword_spaces: 0,
        tessedit_ocr_engine_mode: 1, // 使用 LSTM 引擎
        load_system_dawg: 0,
        load_freq_dawg: 0
      });
      
      // 识别图片
      const { data: { text } } = await worker.recognize(processedImage);
      
      // 提取表达式
      const expression = extractAlternativeExpression(text);
      
      // 计算结果
      const calculationDetails = { steps: [] };
      const result = calculateExpression(expression, calculationDetails);
      
      // 返回结果
      return { 
        result, 
        details: {
          rawOcrResult: text,
          cleanedText: text.trim().replace(/\s+/g, ''),
          expression,
          calculation: calculationDetails.steps.join(' = ')
        }
      };
    } finally {
      // 终止 worker
      await worker.terminate();
    }
  } catch (error) {
    throw new Error('Failed to recognize captcha: ' + error.message);
  }
};

npm install

npm start

{
  "test_cases": [
    {
      "id": 1,
      "name": "Test Case 1",
      "description": "Simple addition",
      "image": "test-captcha",
      "expected_result": 6
    }
  ]
}

node test-captcha-api.js

// 示例：使用 Fetch API 调用验证码识别服务
async function recognizeCaptcha(imageBase64) {
  try {
    const response = await fetch('http://localhost:3000/api/captcha/recognize', {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({ image: imageBase64 })
    });
    
    const data = await response.json();
    return data.result;
  } catch (error) {
    console.error('Error recognizing captcha:', error);
    return null;
  }
}

// 建议的图片预处理步骤
async function preprocessImage(imageBuffer) {
  const image = await Jimp.read(imageBuffer);
  
  return image
    .greyscale()               // 转换为灰度图
    .threshold({ auto: true }) // 自动二值化
    .resize(200, Jimp.AUTO)    // 放大图片
    .quality(100)              // 提高质量
    .getBufferAsync(Jimp.MIME_PNG);
}

{
	"result": 6,
	"details": {
		"rawOcrResult": "0x8+6=7?\n",
		"cleanedText": "0x8+6=7?",
		"expression": "0*8+6",
		"calculation": "0*8+6 = 0*8=0 = 0+6=6 = 6"
	}
}