偵測煽情露骨內容 (安全搜尋)

「安全搜尋偵測」功能會偵測圖片中的煽情露骨內容，例如成人內容或暴力內容。這項功能會使用五個類別 (adult、spoof、medical、violence 和 racy)，並傳回每個類別出現在特定圖片中的可能性。如要進一步瞭解這些欄位，請參閱「SafeSearchAnnotation」頁面。

安全搜尋偵測要求

設定 Google Cloud 專案和驗證

偵測本機圖片中的煽情露骨內容

您可以使用 Vision API 在本機圖片檔案上執行功能偵測。

針對 REST 要求，請在要求主體中，將圖片檔案的內容傳送為base64 編碼字串。

針對 gcloud 和用戶端程式庫要求，請在要求中指定本機圖片的路徑。

REST

使用任何要求資料之前，請先替換以下項目：

  • BASE64_ENCODED_IMAGE：二進位圖片資料的 Base64 表示法 (ASCII 字串)。這個字串應類似下列字串：
    • /9j/4QAYRXhpZgAA...9tAVx/zDQDlGxn//2Q==
    詳情請參閱「base64 編碼」主題。
  • PROJECT_ID：您的 Google Cloud 專案 ID。

HTTP 方法和網址：

POST https://vision.googleapis.com/v1/images:annotate

JSON 要求主體：

{
  "requests": [
    {
      "image": {
        "content": "BASE64_ENCODED_IMAGE"
      },
      "features": [
        {
          "type": "SAFE_SEARCH_DETECTION"
        },
      ]
    }
  ]
}

如要傳送要求，請選擇以下其中一個選項：

curl

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://vision.googleapis.com/v1/images:annotate"

PowerShell

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://vision.googleapis.com/v1/images:annotate" | Select-Object -Expand Content

您應該會收到如下的 JSON 回應：

{
  "responses": [
    {
      "safeSearchAnnotation": {
        "adult": "UNLIKELY",
        "spoof": "VERY_UNLIKELY",
        "medical": "VERY_UNLIKELY",
        "violence": "LIKELY",
        "racy": "POSSIBLE"
      }
    }
  ]
}

Go

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Go。詳情請參閱 Vision Go API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


// detectSafeSearch gets image properties from the Vision API for an image at the given file path.
func detectSafeSearch(w io.Writer, file string) error {
	ctx := context.Background()

	client, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return err
	}

	f, err := os.Open(file)
	if err != nil {
		return err
	}
	defer f.Close()

	image, err := vision.NewImageFromReader(f)
	if err != nil {
		return err
	}
	props, err := client.DetectSafeSearch(ctx, image, nil)
	if err != nil {
		return err
	}

	fmt.Fprintln(w, "Safe Search properties:")
	fmt.Fprintln(w, "Adult:", props.Adult)
	fmt.Fprintln(w, "Medical:", props.Medical)
	fmt.Fprintln(w, "Racy:", props.Racy)
	fmt.Fprintln(w, "Spoofed:", props.Spoof)
	fmt.Fprintln(w, "Violence:", props.Violence)

	return nil
}

Java

在試用這個範例之前，請先按照 Vision API 快速入門：使用用戶端程式庫中的操作說明設定 Java 環境。詳情請參閱 Vision API Java 參考說明文件。


import com.google.cloud.vision.v1.AnnotateImageRequest;
import com.google.cloud.vision.v1.AnnotateImageResponse;
import com.google.cloud.vision.v1.BatchAnnotateImagesResponse;
import com.google.cloud.vision.v1.Feature;
import com.google.cloud.vision.v1.Image;
import com.google.cloud.vision.v1.ImageAnnotatorClient;
import com.google.cloud.vision.v1.SafeSearchAnnotation;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectSafeSearch {
  public static void detectSafeSearch() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String filePath = "path/to/your/image/file.jpg";
    detectSafeSearch(filePath);
  }

  // Detects whether the specified image has features you would want to moderate.
  public static void detectSafeSearch(String filePath) throws IOException {
    List<AnnotateImageRequest> requests = new ArrayList<>();

    ByteString imgBytes = ByteString.readFrom(new FileInputStream(filePath));

    Image img = Image.newBuilder().setContent(imgBytes).build();
    Feature feat = Feature.newBuilder().setType(Feature.Type.SAFE_SEARCH_DETECTION).build();
    AnnotateImageRequest request =
        AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
    requests.add(request);

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
      BatchAnnotateImagesResponse response = client.batchAnnotateImages(requests);
      List<AnnotateImageResponse> responses = response.getResponsesList();

      for (AnnotateImageResponse res : responses) {
        if (res.hasError()) {
          System.out.format("Error: %s%n", res.getError().getMessage());
          return;
        }

        // For full list of available annotations, see http://g.co/cloud/vision/docs
        SafeSearchAnnotation annotation = res.getSafeSearchAnnotation();
        System.out.format(
            "adult: %s%nmedical: %s%nspoofed: %s%nviolence: %s%nracy: %s%n",
            annotation.getAdult(),
            annotation.getMedical(),
            annotation.getSpoof(),
            annotation.getViolence(),
            annotation.getRacy());
      }
    }
  }
}

Node.js

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Node.js。詳情請參閱 Vision Node.js API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

const vision = require('@google-cloud/vision');

// Creates a client
const client = new vision.ImageAnnotatorClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const fileName = 'Local image file, e.g. /path/to/image.png';

// Performs safe search detection on the local file
const [result] = await client.safeSearchDetection(fileName);
const detections = result.safeSearchAnnotation;
console.log('Safe search:');
console.log(`Adult: ${detections.adult}`);
console.log(`Medical: ${detections.medical}`);
console.log(`Spoof: ${detections.spoof}`);
console.log(`Violence: ${detections.violence}`);
console.log(`Racy: ${detections.racy}`);

Python

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Python。詳情請參閱 Vision Python API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

def detect_safe_search(path):
    """Detects unsafe features in the file."""
    from google.cloud import vision

    client = vision.ImageAnnotatorClient()

    with open(path, "rb") as image_file:
        content = image_file.read()

    image = vision.Image(content=content)

    response = client.safe_search_detection(image=image)
    safe = response.safe_search_annotation

    # Names of likelihood from google.cloud.vision.enums
    likelihood_name = (
        "UNKNOWN",
        "VERY_UNLIKELY",
        "UNLIKELY",
        "POSSIBLE",
        "LIKELY",
        "VERY_LIKELY",
    )
    print("Safe search:")

    print(f"adult: {likelihood_name[safe.adult]}")
    print(f"medical: {likelihood_name[safe.medical]}")
    print(f"spoofed: {likelihood_name[safe.spoof]}")
    print(f"violence: {likelihood_name[safe.violence]}")
    print(f"racy: {likelihood_name[safe.racy]}")

    if response.error.message:
        raise Exception(
            "{}\nFor more info on error messages, check: "
            "https://cloud.google.com/apis/design/errors".format(response.error.message)
        )

在遠端圖片上偵測煽情露骨內容

您可以使用 Vision API，針對位於 Cloud Storage 或網際網路上的遠端圖片檔案執行功能偵測。如要傳送遠端檔案要求，請在要求內文中指定檔案的網頁網址或 Cloud Storage URI。

REST

使用任何要求資料之前，請先替換以下項目：

  • CLOUD_STORAGE_IMAGE_URI：Cloud Storage 值區中有效圖片檔案的路徑。您至少必須具備檔案的讀取權限。示例： 
    • gs://my-storage-bucket/img/image1.png
  • PROJECT_ID：您的 Google Cloud 專案 ID。

HTTP 方法和網址：

POST https://vision.googleapis.com/v1/images:annotate

JSON 要求主體：

{
  "requests": [
    {
      "image": {
        "source": {
          "imageUri": "CLOUD_STORAGE_IMAGE_URI"
        }
      },
      "features": [
        {
          "type": "SAFE_SEARCH_DETECTION"
        }
      ]
    }
  ]
}

如要傳送要求，請選擇以下其中一個選項：

curl

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "x-goog-user-project: PROJECT_ID" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://vision.googleapis.com/v1/images:annotate"

PowerShell

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = "PROJECT_ID" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://vision.googleapis.com/v1/images:annotate" | Select-Object -Expand Content

您應該會收到如下的 JSON 回應：

{
  "responses": [
    {
      "safeSearchAnnotation": {
        "adult": "UNLIKELY",
        "spoof": "VERY_UNLIKELY",
        "medical": "VERY_UNLIKELY",
        "violence": "LIKELY",
        "racy": "POSSIBLE"
      }
    }
  ]
}

Go

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Go。詳情請參閱 Vision Go API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


// detectSafeSearch gets image properties from the Vision API for an image at the given file path.
func detectSafeSearchURI(w io.Writer, file string) error {
	ctx := context.Background()

	client, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return err
	}

	image := vision.NewImageFromURI(file)
	props, err := client.DetectSafeSearch(ctx, image, nil)
	if err != nil {
		return err
	}

	fmt.Fprintln(w, "Safe Search properties:")
	fmt.Fprintln(w, "Adult:", props.Adult)
	fmt.Fprintln(w, "Medical:", props.Medical)
	fmt.Fprintln(w, "Racy:", props.Racy)
	fmt.Fprintln(w, "Spoofed:", props.Spoof)
	fmt.Fprintln(w, "Violence:", props.Violence)

	return nil
}

Java

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Java。詳情請參閱 Vision Java API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


import com.google.cloud.vision.v1.AnnotateImageRequest;
import com.google.cloud.vision.v1.AnnotateImageResponse;
import com.google.cloud.vision.v1.BatchAnnotateImagesResponse;
import com.google.cloud.vision.v1.Feature;
import com.google.cloud.vision.v1.Feature.Type;
import com.google.cloud.vision.v1.Image;
import com.google.cloud.vision.v1.ImageAnnotatorClient;
import com.google.cloud.vision.v1.ImageSource;
import com.google.cloud.vision.v1.SafeSearchAnnotation;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectSafeSearchGcs {

  public static void detectSafeSearchGcs() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String filePath = "gs://your-gcs-bucket/path/to/image/file.jpg";
    detectSafeSearchGcs(filePath);
  }

  // Detects whether the specified image on Google Cloud Storage has features you would want to
  // moderate.
  public static void detectSafeSearchGcs(String gcsPath) throws IOException {
    List<AnnotateImageRequest> requests = new ArrayList<>();

    ImageSource imgSource = ImageSource.newBuilder().setGcsImageUri(gcsPath).build();
    Image img = Image.newBuilder().setSource(imgSource).build();
    Feature feat = Feature.newBuilder().setType(Type.SAFE_SEARCH_DETECTION).build();
    AnnotateImageRequest request =
        AnnotateImageRequest.newBuilder().addFeatures(feat).setImage(img).build();
    requests.add(request);

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (ImageAnnotatorClient client = ImageAnnotatorClient.create()) {
      BatchAnnotateImagesResponse response = client.batchAnnotateImages(requests);
      List<AnnotateImageResponse> responses = response.getResponsesList();

      for (AnnotateImageResponse res : responses) {
        if (res.hasError()) {
          System.out.format("Error: %s%n", res.getError().getMessage());
          return;
        }

        // For full list of available annotations, see http://g.co/cloud/vision/docs
        SafeSearchAnnotation annotation = res.getSafeSearchAnnotation();
        System.out.format(
            "adult: %s%nmedical: %s%nspoofed: %s%nviolence: %s%nracy: %s%n",
            annotation.getAdult(),
            annotation.getMedical(),
            annotation.getSpoof(),
            annotation.getViolence(),
            annotation.getRacy());
      }
    }
  }
}

Node.js

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Node.js。詳情請參閱 Vision Node.js API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

// Imports the Google Cloud client libraries
const vision = require('@google-cloud/vision');

// Creates a client
const client = new vision.ImageAnnotatorClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const bucketName = 'Bucket where the file resides, e.g. my-bucket';
// const fileName = 'Path to file within bucket, e.g. path/to/image.png';

// Performs safe search property detection on the remote file
const [result] = await client.safeSearchDetection(
  `gs://${bucketName}/${fileName}`
);
const detections = result.safeSearchAnnotation;
console.log(`Adult: ${detections.adult}`);
console.log(`Spoof: ${detections.spoof}`);
console.log(`Medical: ${detections.medical}`);
console.log(`Violence: ${detections.violence}`);

Python

在試用這個範例之前，請先按照 使用用戶端程式庫的 Vision 快速入門中的操作說明設定 Python。詳情請參閱 Vision Python API 參考說明文件。

如要向 Vision 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

def detect_safe_search_uri(uri):
    """Detects unsafe features in the file located in Google Cloud Storage or
    on the Web."""
    from google.cloud import vision

    client = vision.ImageAnnotatorClient()
    image = vision.Image()
    image.source.image_uri = uri

    response = client.safe_search_detection(image=image)
    safe = response.safe_search_annotation

    # Names of likelihood from google.cloud.vision.enums
    likelihood_name = (
        "UNKNOWN",
        "VERY_UNLIKELY",
        "UNLIKELY",
        "POSSIBLE",
        "LIKELY",
        "VERY_LIKELY",
    )
    print("Safe search:")

    print(f"adult: {likelihood_name[safe.adult]}")
    print(f"medical: {likelihood_name[safe.medical]}")
    print(f"spoofed: {likelihood_name[safe.spoof]}")
    print(f"violence: {likelihood_name[safe.violence]}")
    print(f"racy: {likelihood_name[safe.racy]}")

    if response.error.message:
        raise Exception(
            "{}\nFor more info on error messages, check: "
            "https://cloud.google.com/apis/design/errors".format(response.error.message)
        )

gcloud

如要執行 SafeSearch 偵測，請使用 gcloud ml vision detect-safe-search 指令，如以下範例所示：

gcloud ml vision detect-safe-search gs://my_bucket/input_file