> For the complete documentation index, see [llms.txt](https://neuraldefend.gitbook.io/neural-defend/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://neuraldefend.gitbook.io/neural-defend/unified-image-detection-old.md).

# Unified Image detection - Old

### 🔐 NeuroVerify API – Combined AI Image Detection

#### `POST` 

**🔗 Endpoint**

```json
https://deepscan.neuraldefend.com/detect/unified
```

## /detect/unified

**Unified detection** combining **Liveness + Faceswap + Deepfake** analysis in a single sequential pipeline.

***

### Endpoint Details

| Property           | Value                                 |
| ------------------ | ------------------------------------- |
| **URL**            | `/detect/unified`                     |
| **Method**         | `POST`                                |
| **Content-Type**   | `multipart/form-data`                 |
| **Authentication** | API Key required (`x-api-key` header) |

***

### Detection Flow

The endpoint runs three detection models in sequence with **cascading logic**:

```
┌─────────────────────────────────────────────────────────────┐
│                    UNIFIED DETECTION FLOW                    │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  STEP 0: Face Detection                                      │
│    ├── No Face     → Return NO_FACE                         │
│    ├── Multi Face  → Return MULTI_FACE                      │
│    └── Single Face → Continue                               │
│                      ↓                                       │
│  STEP 1: Liveness Detection (full image)                    │
│    ├── SPOOF       → Stop & Return SPOOF                    │
│    └── REAL        → Continue                               │
│                      ↓                                       │
│  STEP 2: Faceswap Detection (cropped face)                  │
│    ├── FACESWAP    → Stop & Return FACESWAP                 │
│    └── GENUINE     → Continue                               │
│                      ↓                                       │
│  STEP 3: Deepfake Detection (full image)                    │
│    ├── AI_GENERATED → Return AI_GENERATED                   │
│    └── GENUINE      → Return GENUINE                        │
│                                                              │
└─────────────────────────────────────────────────────────────┘
```

#### Optimization

* **Single face detection**: Face is detected once and reused
* **Face cropping**: Cropped face is shared between faceswap and deepfake checks
* **Early stopping**: Pipeline stops as soon as manipulation is detected

***

### Supported Image Formats

| Format | MIME Type                 | File Extensions  | Notes                  |
| ------ | ------------------------- | ---------------- | ---------------------- |
| JPEG   | `image/jpeg`, `image/jpg` | `.jpg`, `.jpeg`  | **Recommended**        |
| PNG    | `image/png`               | `.png`           | Supports transparency  |
| BMP    | `image/bmp`               | `.bmp`           | Windows bitmap format  |
| TIFF   | `image/tiff`              | `.tiff`, `.tif`  | High-quality format    |
| WebP   | `image/webp`              | `.webp`          | Modern format          |
| HEIC   | `image/heic`              | `.heic`, `.heif` | Auto-converted to JPEG |

***

### File Size Limits

| Limit             | Value     | Notes                                       |
| ----------------- | --------- | ------------------------------------------- |
| Maximum File Size | **10 MB** | Files exceeding this limit will be rejected |

***

### Face Detection Requirements

#### Single Face Required

* **Exactly one face** required in the image
* Multiple faces → `MULTI_FACE` response
* No face → `NO_FACE` response

#### Rotation Support 🔄

* EXIF orientation automatically corrected
* Handles rotated images (90°, 180°, 270°)

***

### Request Format

#### Headers

| Header         | Required | Description           |
| -------------- | -------- | --------------------- |
| `x-api-key`    | Yes      | Your API key          |
| `Content-Type` | Yes      | `multipart/form-data` |

#### Body

| Field  | Type | Required | Description           |
| ------ | ---- | -------- | --------------------- |
| `file` | File | Yes      | Image file to analyze |

#### Example Request (cURL)

```bash
curl -X POST "https://deepscan.neuraldefend.com/detect/unified" \
  -H "x-api-key: your-api-key" \
  -F "file=@/path/to/image.jpg"
```

#### Example Request (Python)

```python
import requests

url = "https://deepscan.neuraldefend.com/detect/unified"
headers = {"x-api-key": "your-api-key"}
files = {"file": open("image.jpg", "rb")}

response = requests.post(url, headers=headers, files=files)
print(response.json())
```

***

### Response Format

#### Success Response Structure

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_a1b2c3d4e5f6789012ab",
    "filename": "photo.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 1,
    "billable": "Y",
    "message": "All verification checks passed successfully",
    "inference_time": 1.234,
    "original_filename": "photo.jpg",
    "face_count": 1,
    "face_confidence": 0.95,
    "prediction_tag": "GENUINE",
    "final_prediction": "Genuine - All checks passed",
    "liveness_check": {
      "prediction": "Real",
      "confidence": 0.987,
      "inference_time": 0.321,
      "status": "performed"
    },
    "faceswap_check": {
      "prediction": "Genuine",
      "confidence": 0.945,
      "inference_time": 0.412,
      "status": "performed"
    },
    "deepfake_check": {
      "prediction": "Genuine",
      "confidence": 0.923,
      "inference_time": 0.501,
      "status": "performed"
    }
  }
}
```

#### Response Field Descriptions

| Field              | Type       | Description                     |
| ------------------ | ---------- | ------------------------------- |
| `unique_trx_id`    | string     | Unique transaction identifier   |
| `filename`         | string     | Uploaded filename               |
| `content_type`     | string     | MIME type                       |
| `status`           | string     | `"success"` or `"failed"`       |
| `status_code`      | integer    | Status code (1-8)               |
| `billable`         | string     | `"Y"` or `"N"`                  |
| `message`          | string     | Human-readable result message   |
| `inference_time`   | float      | Total processing time (seconds) |
| `face_count`       | integer    | Number of faces detected        |
| `face_confidence`  | float/null | Face detection confidence       |
| `prediction_tag`   | string     | Final classification            |
| `final_prediction` | string     | Human-readable verdict          |
| `liveness_check`   | object     | Liveness detection result       |
| `faceswap_check`   | object     | Faceswap detection result       |
| `deepfake_check`   | object     | Deepfake detection result       |

#### Check Object Structure

Each check (`liveness_check`, `faceswap_check`, `deepfake_check`) contains:

| Field            | Type        | Description                               |
| ---------------- | ----------- | ----------------------------------------- |
| `prediction`     | string/null | Detection result                          |
| `confidence`     | float/null  | Confidence score (0.0-1.0)                |
| `inference_time` | float/null  | Processing time (seconds)                 |
| `status`         | string      | `"performed"`, `"skipped"`, or `"failed"` |
| `skip_reason`    | string      | Reason if skipped (optional)              |

***

### Prediction Tags Reference

#### Final Verdict Tags

| Tag            | Scenario          | Description                                    |
| -------------- | ----------------- | ---------------------------------------------- |
| `GENUINE`      | All checks passed | Image is genuine, live person, no manipulation |
| `SPOOF`        | Liveness failed   | Not a live person (photo/screen attack)        |
| `FACESWAP`     | Faceswap detected | Face manipulation detected                     |
| `AI_GENERATED` | Deepfake detected | AI-generated content detected                  |

#### Face Detection Tags

| Tag          | Scenario       | Description                 |
| ------------ | -------------- | --------------------------- |
| `NO_FACE`    | No face found  | No human face detected      |
| `MULTI_FACE` | Multiple faces | More than one face detected |

#### Error Tags

| Tag                | Scenario                   | Description                               |
| ------------------ | -------------------------- | ----------------------------------------- |
| `INVALID_FORMAT`   | Bad file type              | Unsupported file format                   |
| `FILE_TOO_LARGE`   | Size > 10MB                | File exceeds limit                        |
| `INVALID_SIZE`     | Resolution too low         | Image dimensions below minimum            |
| `IMAGE_TOO_LARGE`  | Resolution too large       | Image dimensions exceed maximum           |
| `BRIGHTNESS_ERROR` | Too dark/bright            | Image brightness outside acceptable range |
| `CONTRAST_ERROR`   | Low contrast               | Insufficient contrast in image            |
| `BLUR_ERROR`       | Too blurry                 | Image is out of focus or blurry           |
| `QUALITY_ERROR`    | Generic quality failure    | General image quality check failed        |
| `CONVERSION_ERROR` | HEIC conversion failed     | HEIC file could not be converted          |
| `Security-Error`   | Security validation failed | Security check failed                     |
| `Validation-Error` | Generic validation failed  | Validation check failed                   |
| `Processing-Error` | Processing error           | Error during processing                   |

***

### Status Code Mapping

| Status Code | Billable | Scenario                 |
| ----------- | -------- | ------------------------ |
| 1           | Y        | Successful analysis      |
| 2           | N        | Bad request (validation) |
| 5           | N        | Internal server error    |
| 6           | Y        | No face detected         |
| 7           | Y        | Multiple faces detected  |

***

### Response Scenarios

#### 1. All Checks Passed - GENUINE

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_a1b2c3d4e5f6789012ab",
    "filename": "selfie.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 1,
    "billable": "Y",
    "message": "All verification checks passed successfully",
    "inference_time": 1.234,
    "original_filename": "selfie.jpg",
    "face_count": 1,
    "face_confidence": 0.95,
    "prediction_tag": "GENUINE",
    "final_prediction": "Genuine - All checks passed",
    "liveness_check": {
      "prediction": "Real",
      "confidence": 0.987,
      "inference_time": 0.321,
      "status": "performed"
    },
    "faceswap_check": {
      "prediction": "Genuine",
      "confidence": 0.945,
      "inference_time": 0.412,
      "status": "performed"
    },
    "deepfake_check": {
      "prediction": "Genuine",
      "confidence": 0.923,
      "inference_time": 0.501,
      "status": "performed"
    }
  }
}
```

#### 2. Spoof Detected (Pipeline Stops at Step 1)

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_b2c3d4e5f67890123bc",
    "filename": "photo_of_photo.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 1,
    "billable": "Y",
    "message": "Spoof detected - Image is not from a live person",
    "inference_time": 0.456,
    "original_filename": "photo_of_photo.jpg",
    "face_count": 1,
    "face_confidence": 0.95,
    "prediction_tag": "SPOOF",
    "final_prediction": "Spoof detected - Image is not from a live person",
    "liveness_check": {
      "prediction": "Spoof",
      "confidence": 0.934,
      "inference_time": 0.321,
      "status": "performed"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Spoof detected in liveness check"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Spoof detected in liveness check"
    }
  }
}
```

#### 3. Faceswap Detected (Pipeline Stops at Step 2)

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_c3d4e5f678901234cd",
    "filename": "faceswap.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 1,
    "billable": "Y",
    "message": "Face manipulation detected",
    "inference_time": 0.789,
    "original_filename": "faceswap.jpg",
    "face_count": 1,
    "face_confidence": 0.95,
    "prediction_tag": "FACESWAP",
    "final_prediction": "Face manipulation detected",
    "liveness_check": {
      "prediction": "Real",
      "confidence": 0.987,
      "inference_time": 0.321,
      "status": "performed"
    },
    "faceswap_check": {
      "prediction": "Face manipulation detected",
      "confidence": 0.912,
      "inference_time": 0.412,
      "status": "performed"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Faceswap detected"
    }
  }
}
```

#### 4. AI-Generated Detected (Pipeline Completes All Steps)

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_d4e5f6789012345de",
    "filename": "ai_generated.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 1,
    "billable": "Y",
    "message": "AI-Generated content detected",
    "inference_time": 1.234,
    "original_filename": "ai_generated.jpg",
    "face_count": 1,
    "face_confidence": 0.95,
    "prediction_tag": "AI_GENERATED",
    "final_prediction": "AI-Generated content detected",
    "liveness_check": {
      "prediction": "Real",
      "confidence": 0.876,
      "inference_time": 0.321,
      "status": "performed"
    },
    "faceswap_check": {
      "prediction": "Genuine",
      "confidence": 0.812,
      "inference_time": 0.412,
      "status": "performed"
    },
    "deepfake_check": {
      "prediction": "AI-Generated content detected",
      "confidence": 0.945,
      "inference_time": 0.501,
      "status": "performed"
    }
  }
}
```

#### 5. No Face Detected

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_e5f67890123456ef",
    "filename": "landscape.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 6,
    "billable": "Y",
    "message": "No face detected, face is too far from camera, or no reliable face suitable for prediction",
    "inference_time": 0.234,
    "original_filename": "landscape.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "NO_FACE",
    "final_prediction": "No face detected, face is too far from camera, or no reliable face suitable for prediction",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "No face detected"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "No face detected"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "No face detected"
    }
  }
}
```

#### 6. Multiple Faces Detected

**HTTP Status:** `200 OK`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_f67890123456789fg",
    "filename": "group_photo.jpg",
    "content_type": "image/jpeg",
    "status": "success",
    "status_code": 7,
    "billable": "Y",
    "message": "Multiple faces detected (4 faces). Single face required.",
    "inference_time": 0.312,
    "original_filename": "group_photo.jpg",
    "face_count": 4,
    "face_confidence": null,
    "prediction_tag": "MULTI_FACE",
    "final_prediction": "Multiple faces detected (4 faces)",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Multiple faces detected (4 faces)"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Multiple faces detected (4 faces)"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Multiple faces detected (4 faces)"
    }
  }
}
```

#### 7. File Too Large

**HTTP Status:** `400 Bad Request`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_g7890123456789agh",
    "filename": "huge_image.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "File size too large. Maximum 10MB allowed.",
    "inference_time": 0.008,
    "original_filename": "huge_image.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "FILE_TOO_LARGE",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "File size too large. Maximum 10MB allowed."
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "File size too large. Maximum 10MB allowed."
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "File size too large. Maximum 10MB allowed."
    }
  }
}
```

#### 8. Invalid Size (Resolution Too Low)

**HTTP Status:** `400 Bad Request`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_xxx",
    "filename": "small_image.jpeg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Image resolution too low (178x218, min=224x224)",
    "inference_time": 0.011,
    "original_filename": "small_image.jpeg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "INVALID_SIZE",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image resolution too low (178x218, min=224x224)"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image resolution too low (178x218, min=224x224)"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image resolution too low (178x218, min=224x224)"
    }
  }
}
```

#### 9. Brightness Error

**HTTP Status:** `400 Bad Request`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_xxx",
    "filename": "overexposed.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Image too bright (brightness=250, max=220)",
    "inference_time": 0.013,
    "original_filename": "overexposed.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "BRIGHTNESS_ERROR",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image too bright (brightness=250, max=220)"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image too bright (brightness=250, max=220)"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Image too bright (brightness=250, max=220)"
    }
  }
}
```

#### 10. Security Error

**HTTP Status:** `400 Bad Request`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_xxx",
    "filename": "malicious.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Security validation failed",
    "inference_time": 0.010,
    "original_filename": "malicious.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "Security-Error",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Security validation failed"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Security validation failed"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Security validation failed"
    }
  }
}
```

#### 11. Validation Error

**HTTP Status:** `400 Bad Request`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_xxx",
    "filename": "invalid.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Validation failed",
    "inference_time": 0.011,
    "original_filename": "invalid.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "Validation-Error",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Validation failed"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Validation failed"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Validation failed"
    }
  }
}
```

#### 12. Detectors Not Initialized (503)

**HTTP Status:** `503 Service Unavailable`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_xxx",
    "filename": "photo.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Detectors not initialized: liveness_detector, faceswap_detector",
    "inference_time": 0.010,
    "original_filename": "photo.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "Processing-Error",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Detectors not initialized: liveness_detector, faceswap_detector"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Detectors not initialized: liveness_detector, faceswap_detector"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Detectors not initialized: liveness_detector, faceswap_detector"
    }
  }
}
```

#### 13. Internal Server Error

**HTTP Status:** `500 Internal Server Error`

```json
{
  "unified_analysis": {
    "unique_trx_id": "trx_h890123456789abhi",
    "filename": "photo.jpg",
    "content_type": "image/jpeg",
    "status": "failed",
    "status_code": 2,
    "billable": "N",
    "message": "Internal server error during unified detection",
    "inference_time": 0.234,
    "original_filename": "photo.jpg",
    "face_count": 0,
    "face_confidence": null,
    "prediction_tag": "Processing-Error",
    "final_prediction": "Validation failed",
    "liveness_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Internal server error during unified detection"
    },
    "faceswap_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Internal server error during unified detection"
    },
    "deepfake_check": {
      "prediction": null,
      "confidence": null,
      "inference_time": null,
      "status": "skipped",
      "skip_reason": "Internal server error during unified detection"
    }
  }
}
```

***

#### 14. Contrast Error

**HTTP Status:** `500 Internal Server Error`

```json
{
    "unified_analysis": {
        "unique_trx_id": "trx_gjuyp08x323rbj9uaiao",
        "filename": "CONTRAST_ERROR.jpg",
        "content_type": "image/jpeg",
        "status": "failed",
        "status_code": 2,
        "billable": "N",
        "message": "Image has low contrast (contrast=18, min=20)",
        "inference_time": 0.002,
        "original_filename": "CONTRAST_ERROR.jpg",
        "face_count": 0,
        "face_confidence": null,
        "prediction_tag": "CONTRAST_ERROR",
        "final_prediction": "Validation failed",
        "liveness_check": {
            "prediction": null,
            "confidence": null,
            "inference_time": null,
            "status": "skipped",
            "skip_reason": "Image has low contrast (contrast=18, min=20)"
        },
        "faceswap_check": {
            "prediction": null,
            "confidence": null,
            "inference_time": null,
            "status": "skipped",
            "skip_reason": "Image has low contrast (contrast=18, min=20)"
        },
        "deepfake_check": {
            "prediction": null,
            "confidence": null,
            "inference_time": null,
            "status": "skipped",
            "skip_reason": "Image has low contrast (contrast=18, min=20)"
        }
    }
}
```

***

### Best Practices

#### ✅ Recommended

* Use **JPEG format** for best compatibility
* Ensure **good lighting** (important for liveness)
* Face should be **clearly visible and frontal**
* Keep file size under **10 MB** for faster processing

#### ❌ Avoid

* ❌ Files larger than 10 MB
* ❌ Images with multiple faces
* ❌ Poor lighting conditions
* ❌ Blurry or low-quality images
* ❌ Extreme face angles

***

### Error Handling

| HTTP Code | Meaning             | Action                   |
| --------- | ------------------- | ------------------------ |
| 200       | Success             | Process the response     |
| 400       | Bad Request         | Check file format/size   |
| 401       | Unauthorized        | Check API key            |
| 500       | Server Error        | Retry or contact support |
| 503       | Service Unavailable | Service not available    |

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://neuraldefend.gitbook.io/neural-defend/unified-image-detection-old.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.