什么是 Didit 年龄估算？

Didit 年龄估算技能提供了一个强大的界面，利用先进的深度学习模型从人脸图像中估算人的年龄。它专为需要在自动化工作流中实现年龄限制、合规性检查或人脸分析的开发人员而设计。通过利用 Openclaw Skills 的这一组件，用户可以实现高精度，对于 18 岁以下的人群，平均绝对误差 (MAE) 低至 1.5 岁。

除了简单的估算，该技能还结合了复杂的活体检测技术以减少欺诈尝试。它支持多种安全级别，包括用于低摩擦消费应用的基于 CNN 的被动检查，以及用于银行和医疗保健等高安全性环境的主动 3D 闪光方法。这使其成为在确保流畅用户体验的同时，维护监管标准的必备工具。

下载入口:https://github.com/openclaw/skills/tree/main/skills/rosasalberto/didit-age-estimation

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Didit 年龄估算 应用场景

• 为受限数字内容或电子商务产品实施年龄准入限制。
• 在金融服务和医疗保健应用程序的注册过程中验证用户年龄。
• 通过结合年龄估算和被动活体检测来增强身份安全。
• 自动执行针对不同国家/地区法定成年法律的合规性检查。

1. 用户通过 Openclaw Skills 界面提供 JPEG、PNG、WebP 或 TIFF 格式的人脸图像。
2. 该技能使用安全的 x-api-key 将图像传输到 Didit 独立 API。
3. API 处理图像以识别单张人脸，并根据面部特征估算年龄。
4. 同时进行活体检测，以确保图像是真人而非欺诈尝试。
5. 系统返回一个完整的 JSON 对象，包含估算年龄、活体置信度分数以及已批准、已拒绝或审核中的状态。

Didit 年龄估算 配置指南

要开始使用此技能，您需要从 Didit 业务控制台获取有效的 API 密钥。获取后，配置您的环境：

# 设置主要环境变量
export DIDIT_API_KEY="your_didit_api_key_here"

确保处理的图像小于 5MB 且包含一张清晰可见的人脸，以便在 Openclaw Skills 中获得最佳性能。

Didit 年龄估算 数据架构与分类体系

该技能将其输出组织成结构化格式，以便轻松集成到更大的工作流中：

name: didit-age-estimation
description: >
  Integrate Didit Age Estimation standalone API to estimate a person's age from a facial image.
  Use when the user wants to estimate age, verify age, implement age gating, check if someone
  is over 18/21, perform age verification for compliance, or use facial analysis for age detection
  using Didit. Includes passive liveness check. Supports configurable thresholds, adaptive age
  estimation with ID verification fallback, and per-country age restrictions.
version: 1.0.0
metadata:
  openclaw:
    requires:
      env:
        - DIDIT_API_KEY
    primaryEnv: DIDIT_API_KEY
    emoji: "??"
    homepage: https://docs.didit.me

Didit Age Estimation API

Overview

Estimates a person's age from a facial image using deep learning. Also performs a passive liveness check to prevent spoofing.

Key constraints:

• Supported formats: JPEG, PNG, WebP, TIFF
• Maximum file size: 5MB
• Image must contain one clearly visible face
• Accuracy: MAE ±3.5 years overall; ±1.5 years for under-18

Capabilities: Age estimation with confidence scoring, gender estimation, passive liveness detection, configurable age thresholds, per-country age restrictions, adaptive mode with ID verification fallback for borderline cases.

Liveness methods (workflow mode):

API Reference: https://docs.didit.me/reference/age-estimation-standalone-api

Authentication

All requests require x-api-key header. Get your key from Didit Business Console → API & Webhooks.

Endpoint

POST https://verification.didit.me/v3/age-estimation/

Headers

Request Parameters (multipart/form-data)

Example

import requests

response = requests.post(
    "https://verification.didit.me/v3/age-estimation/",
    headers={"x-api-key": "YOUR_API_KEY"},
    files={"user_image": ("selfie.jpg", open("selfie.jpg", "rb"), "image/jpeg")},
    data={"vendor_data": "user-123"},
)
print(response.json())

const formData = new FormData();
formData.append("user_image", selfieFile);

const response = await fetch("https://verification.didit.me/v3/age-estimation/", {
  method: "POST",
  headers: { "x-api-key": "YOUR_API_KEY" },
  body: formData,
});

Response (200 OK)

{
  "request_id": "a1b2c3d4-...",
  "liveness": {
    "status": "Approved",
    "method": "PASSIVE",
    "score": 89.92,
    "age_estimation": 24.3,
    "reference_image": "https://example.com/reference.jpg",
    "video_url": null,
    "warnings": []
  },
  "created_at": "2025-05-01T13:11:07.977806Z"
}

Status Values & Handling

Error Responses

Response Field Reference

Accuracy by Age Range

Warning Tags

Auto-Decline

Configurable (Decline / Review / Approve)

Warning severity: error (→ Declined), warning (→ In Review), information (no effect).

Common Workflows

Basic Age Gate

1. Capture user selfie
2. POST /v3/age-estimation/ → {"user_image": selfie}
3. Check liveness.age_estimation >= your_minimum_age
4. If "Approved" → user meets age requirement
   If "Declined" → check warnings for AGE_BELOW_MINIMUM or liveness failure

Adaptive Age Estimation (Workflow Mode)

1. Configure workflow with age thresholds in Console
2. POST /v3/session/ → create session with age-estimation workflow
3. User takes selfie → system estimates age
4. Clear pass (well above threshold) → Approved instantly
   Clear fail (well below threshold) → Declined
   Borderline case → automatic ID verification fallback
5. If ID fallback triggered: per-country age restrictions apply

Per-Country Age Restrictions

Configure in Console per issuing country:

Use "Apply age of majority" button in Console to auto-populate defaults.