---
title: HaS_Image_0209_FP32
canonical_url: "https://www.modelscope.cn/models/TencentXuanwu/HaS_Image_0209_FP32"
md_url: "https://www.modelscope.cn/models/TencentXuanwu/HaS_Image_0209_FP32.md"
repository: TencentXuanwu/HaS_Image_0209_FP32
last_updated: 2026-03-04
license: mit
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
library_name:
  - pytorch
frameworks:
  - Pytorch
language:
  - zh
  - en
downloads: 34
stars: 3
---

# HaS_Image_0209_FP32

> HaS_Image_0209_FP32 - TencentXuanwu 在 ModelScope 开源的模型。HaS Image Model (FP32)

TencentXuanwu/HaS_Image_0209_FP32 是 ModelScope 魔搭社区上的image-segmentation模型，采用 mit 许可。

- **Repository**: TencentXuanwu/HaS_Image_0209_FP32
- **License**: mit
- **Tasks**: image-segmentation
- **Downloads**: 34
- **Stars**: 3
- **Last updated**: 2026-03-04

Source: https://www.modelscope.cn/models/TencentXuanwu/HaS_Image_0209_FP32

---

# HaS Image Model (FP32)

**HaS（Hide and Seek）** 是一个端侧部署的图像隐私模型，对图片中的隐私区域进行像素级识别和分割。

- 📦 **基于 YOLO11** 实例分割，FP32 精度，119 MB
- 🔒 **数据不出设备**，本地推理，无需联网
- 🎯 **21 类隐私类别**，覆盖生物特征、证件、金融卡、屏幕等
- ⚡ **单张图片 ~20ms** 推理速度

## 一、核心能力

传统图像脱敏依赖人脸检测器或手动遮挡。HaS Image 是一个**端侧隐私分割模型**——识别 21 类敏感内容，提供像素级掩码，实现精准自动化脱敏。

| 能力 | 说明 |
|------|------|
| **21 类隐私类别** | 覆盖生物特征（人脸、指纹、掌纹）、证件（身份证、护照、通行证）、金融（银行卡）、屏幕（手机、显示器）等 |
| **像素级分割** | 实例分割而非仅边界框——掩码精确贴合每个敏感区域的轮廓 |
| **多种遮挡方式** | 支持马赛克、高斯模糊、纯色填充——可按场景配置强度和样式 |
| **批量处理** | 一条命令处理整个目录的图片 |
| **类别过滤** | 选择性脱敏指定类别（如仅人脸，或人脸+车牌） |
| **高速推理** | 单张图片 ~20ms，适合实时和批量工作流 |

## 二、支持的隐私类别

6 大分组，21 个类别：

| 分组 | ID | 类别 | 中文 |
|------|----|------|------|
| **生物特征** | 0 | `face` | 人脸 |
| | 1 | `fingerprint` | 指纹 |
| | 2 | `palmprint` | 掌纹 |
| **证件** | 3 | `id_card` | 身份证 |
| | 4 | `hk_macau_permit` | 港澳通行证 |
| | 5 | `passport` | 护照 |
| | 6 | `employee_badge` | 工牌 |
| **交通** | 7 | `license_plate` | 车牌 |
| **金融** | 8 | `bank_card` | 银行卡 |
| **安全** | 9 | `physical_key` | 钥匙 |
| **文档** | 10 | `receipt` | 收据 |
| | 11 | `shipping_label` | 快递单 |
| | 12 | `official_seal` | 公章 |
| | 20 | `paper` | 纸张 |
| **信息载体** | 13 | `whiteboard` | 白板 |
| | 14 | `sticky_note` | 便签 |
| | 15 | `mobile_screen` | 手机屏幕 |
| | 16 | `monitor_screen` | 显示器屏幕 |
| **医疗** | 17 | `medical_wristband` | 医用腕带 |
| **编码** | 18 | `qr_code` | 二维码 |
| | 19 | `barcode` | 条形码 |

类别过滤支持英文名、中文名或数字 ID，逗号分隔。

## 三、快速开始

### 安装

```bash
pip install ultralytics
```

### Python 使用

```python
from ultralytics import YOLO

model = YOLO("sensitive_seg_best.pt")

# 检测所有隐私区域
results = model.predict("photo.jpg", conf=0.25)

# 处理结果
for result in results:
    for box, mask in zip(result.boxes, result.masks):
        category_id = int(box.cls)
        confidence = float(box.conf)
        print(f"类别: {category_id}, 置信度: {confidence:.2f}")
```

### CLI 使用（通过 HaS）

HaS 配套了 CLI 工具 `has-image`，将模型封装为开箱即用的命令：

```bash
# 扫描——仅检测隐私区域，不修改图片
has-image scan --image photo.jpg

# 脱敏——检测并遮挡（默认马赛克）
has-image hide --image photo.jpg

# 脱敏——仅遮挡人脸，使用高斯模糊
has-image hide --image photo.jpg --types face --method blur --strength 25

# 批量处理整个目录
has-image hide --dir ./photos/ --output-dir ./redacted/
```

## 四、遮挡方式

| 方式 | 参数 | 说明 |
|------|------|------|
| **马赛克** | `--method mosaic` | 像素化方块（默认）。`--strength` 控制块大小 |
| **高斯模糊** | `--method blur` | 平滑模糊。`--strength` 控制模糊半径 |
| **纯色填充** | `--method fill` | 纯色覆盖。`--fill-color` 设置十六进制颜色（默认 `#000000`） |

## 五、使用场景

| 场景 | 说明 | 方法 |
|------|------|------|
| **照片发布** | 分享照片前遮挡人脸和车牌 | `hide --types face,license_plate` |
| **文档脱敏** | 遮挡扫描件中的身份证、银行卡、公章 | `hide --types id_card,bank_card,official_seal` |
| **数据集匿名化** | 批量匿名化 ML 训练数据集中的图片 | `hide --dir ./dataset/` |
| **合规审查** | 上传图片处理前扫描敏感内容 | `scan --image uploaded.jpg` |
| **视频帧处理** | 抽帧 → 逐帧脱敏 → 重新组装 | 逐帧 `hide` |
| **录屏隐私** | 遮挡录屏中的手机/显示器屏幕 | `hide --types mobile_screen,monitor_screen` |

## 六、脱敏示例

![image](Figure.png)

<p align="center"><em>图 1. HaS Image 模型脱敏前后对比</em></p>

## 七、模型规格

| 属性 | 值 |
|------|-----|
| 架构 | YOLO11 实例分割 |
| 精度 | FP32 |
| 文件大小 | 119 MB |
| 任务 | 实例分割 |
| 类别数 | 21 类隐私实体 |
| 推理速度 | 单张图片 ~20ms |
| 输入 | 任意分辨率（自动缩放） |
| 输出 | 边界框 + 像素级掩码 + 置信度分数 |
| 框架 | Ultralytics |
| 许可证 | MIT |

## 八、相关模型

| 模型 | 类型 | 说明 |
|------|------|------|
| [HaS Text Q8_0](https://huggingface.co/xuanwulab/HaS_Text_0209_0.6B_Q8) | 文本 | 文本脱敏，0.6B 参数，Q8_0 量化，639 MB |
| [HaS Text Q4_K_M](https://huggingface.co/xuanwulab/HaS_Text_0209_0.6B_Q4) | 文本 | 文本脱敏，0.6B 参数，Q4_K_M 量化，397 MB |
| **HaS Image FP32** | 图像 | 图像隐私分割，YOLO11，FP32，119 MB |

> HaS Text 处理文本脱敏（命名实体、个人信息）；HaS Image 处理图像脱敏（视觉隐私区域）。二者结合，提供完整的端侧文本+图像隐私保护方案。

---

<details>
<summary><b>English Version</b></summary>

# HaS Image Model (FP32)

**HaS (Hide and Seek)** is an on-device image privacy model that performs pixel-level detection and segmentation of sensitive regions in images.

- 📦 **YOLO11-based** instance segmentation, FP32, 119 MB
- 🔒 **Data never leaves device** — local inference, no network required
- 🎯 **21 privacy categories** covering biometrics, ID documents, financial cards, screens, and more
- ⚡ **~20ms per image** inference speed on modern hardware

## 1. Core Capabilities

| Capability | Description |
|------------|-------------|
| **21 Privacy Categories** | Covers biometrics (face, fingerprint, palmprint), ID documents (ID card, passport, permit), financial (bank card), screens (mobile, monitor), and more |
| **Pixel-Level Segmentation** | Instance segmentation, not just bounding boxes — masks follow the exact contour of each sensitive region |
| **Multiple Redaction Methods** | Supports mosaic, Gaussian blur, and solid fill — configurable strength and style per use case |
| **Batch Processing** | Process entire directories of images in one command |
| **Category Filtering** | Selectively redact only specific categories (e.g., faces only, or faces + license plates) |
| **High Speed** | ~20ms per image, suitable for real-time and batch workflows |

## 2. Supported Privacy Categories

6 groups, 21 categories:

| Group | ID | Category | Description |
|-------|----|----------|-------------|
| **Biometrics** | 0 | `face` | Human faces |
| | 1 | `fingerprint` | Fingerprints |
| | 2 | `palmprint` | Palm prints |
| **ID Documents** | 3 | `id_card` | National ID cards |
| | 4 | `hk_macau_permit` | HK/Macau travel permits |
| | 5 | `passport` | Passports |
| | 6 | `employee_badge` | Employee badges |
| **Transportation** | 7 | `license_plate` | Vehicle license plates |
| **Financial** | 8 | `bank_card` | Bank/credit cards |
| **Security** | 9 | `physical_key` | Physical keys |
| **Documents** | 10 | `receipt` | Receipts |
| | 11 | `shipping_label` | Shipping/courier labels |
| | 12 | `official_seal` | Official stamps/seals |
| | 20 | `paper` | Paper documents |
| **Information Carriers** | 13 | `whiteboard` | Whiteboards |
| | 14 | `sticky_note` | Sticky notes |
| | 15 | `mobile_screen` | Mobile phone screens |
| | 16 | `monitor_screen` | Computer monitor screens |
| **Medical** | 17 | `medical_wristband` | Hospital wristbands |
| **Codes** | 18 | `qr_code` | QR codes |
| | 19 | `barcode` | Barcodes |

## 3. Quick Start

```bash
pip install ultralytics
```

```python
from ultralytics import YOLO

model = YOLO("sensitive_seg_best.pt")
results = model.predict("photo.jpg", conf=0.25)

for result in results:
    for box, mask in zip(result.boxes, result.masks):
        category_id = int(box.cls)
        confidence = float(box.conf)
        print(f"Category: {category_id}, Confidence: {confidence:.2f}")
```

## 4. Redaction Methods

| Method | Flag | Description |
|--------|------|-------------|
| **Mosaic** | `--method mosaic` | Pixelated blocks (default). `--strength` controls block size |
| **Gaussian Blur** | `--method blur` | Smooth blur. `--strength` controls blur radius |
| **Solid Fill** | `--method fill` | Solid color overlay. `--fill-color` sets hex color (default `#000000`) |

## 5. Redaction Example

![image](Figure.png)

<p align="center"><em>Figure 1. Before and after privacy redaction with HaS Image model</em></p>

## 6. Model Specifications

| Property | Value |
|----------|-------|
| Architecture | YOLO11 Instance Segmentation |
| Precision | FP32 |
| File Size | 119 MB |
| Categories | 21 privacy classes |
| Inference Speed | ~20ms per image |
| Framework | Ultralytics |
| License | MIT |

## 7. Related Models

| Model | Type | Description |
|-------|------|-------------|
| [HaS Text Q8_0](https://huggingface.co/xuanwulab/HaS_Text_0209_0.6B_Q8) | Text | Text anonymization, 0.6B params, Q8_0, 639 MB |
| [HaS Text Q4_K_M](https://huggingface.co/xuanwulab/HaS_Text_0209_0.6B_Q4) | Text | Text anonymization, 0.6B params, Q4_K_M, 397 MB |
| **HaS Image FP32** | Image | Image privacy segmentation, YOLO11, FP32, 119 MB |

> HaS Text handles text anonymization (named entities, PII); HaS Image handles image anonymization (visual privacy regions). Together they provide a complete on-device privacy solution for both text and images.

</details>