使用指令列偵測圖片中的標籤

使用指令列偵測圖片中的標籤

這個頁面說明如何使用 REST 介面和 curl 指令，將三個特徵偵測和註解要求傳送至 Vision API。

Vision API 可將 Google 影像辨識技術輕鬆整合至開發人員應用程式，您可以將圖片資料和所需功能類型傳送至 Vision API，然後根據您感興趣的圖片屬性，取得相應的回覆。如要進一步瞭解提供的功能類型，請參閱「所有 Vision API 功能清單」。

事前準備

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
Install the Google Cloud CLI.
If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.
To initialize the gcloud CLI, run the following command:
gcloud init
Create or select a Google Cloud project.
Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.
• Create a Google Cloud project:

  gcloud projects create PROJECT_ID

  Replace PROJECT_ID with a name for the Google Cloud project you are creating.

• Select the Google Cloud project that you created:

  gcloud config set project PROJECT_ID

  Replace PROJECT_ID with your Google Cloud project name.
Make sure that billing is enabled for your Google Cloud project.
Enable the Vision API:
gcloud services enable vision.googleapis.com
Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/storage.objectViewer
gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE
• Replace PROJECT_ID with your project ID.

• Replace USER_IDENTIFIER with the identifier for your user account. For example, user:[e-mail].

• Replace ROLE with each individual role.

Install the Google Cloud CLI.

If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

To initialize the gcloud CLI, run the following command:

gcloud init

Create or select a Google Cloud project.

Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

• Create a Google Cloud project:

  gcloud projects create PROJECT_ID

  Replace PROJECT_ID with a name for the Google Cloud project you are creating.

• Select the Google Cloud project that you created:

  gcloud config set project PROJECT_ID

  Replace PROJECT_ID with your Google Cloud project name.

Make sure that billing is enabled for your Google Cloud project.

Enable the Vision API:

gcloud services enable vision.googleapis.com

Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/storage.objectViewer

gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE

• Replace PROJECT_ID with your project ID.

• Replace USER_IDENTIFIER with the identifier for your user account. For example, user:[e-mail].

• Replace ROLE with each individual role.

發出圖片註解要求

完成「事前準備」步驟後，即可使用 Vision API 為圖片檔加上註解。

在本範例中，您會使用 curl 傳送要求至 Vision API，並使用下列圖片：

Cloud Storage URI：

gs://cloud-samples-data/vision/using_curl/shanghai.jpeg

HTTPS 網址：

https://console.cloud.google.com/storage/browser/cloud-samples-data/vision/using_curl/shanghai.jpeg



圖片來源： Unsplash 的 Steve Long。

建立要求 JSON

下列 request.json 檔案示範如何要求三項 images:annotate 功能，並限制回應中的結果。

建立具有下列文字的 JSON 要求檔案，並將檔案儲存為工作目錄中的 request.json 純文字檔案：

request.json

{
  "requests": [
    {
      "image": {
        "source": {
          "imageUri": "gs://cloud-samples-data/vision/using_curl/shanghai.jpeg"
        }
      },
      "features": [
        {
          "type": "LABEL_DETECTION",
          "maxResults": 3
        },
        {
          "type": "OBJECT_LOCALIZATION",
          "maxResults": 1
        },
        {
          "type": "TEXT_DETECTION",
          "maxResults": 1,
          "model": "builtin/latest"
        }
      ]
    }
  ]
}

欄位值詳細資料

• image.source.gcsImageUri - 表示儲存在 Cloud Storage 值區中的圖片。您可以將這項要求變更為 image.source.imageUri，以取得公開可用的 URI，或是變更為 image.content，以傳遞圖片的 base64 編碼字串表示法。
• features - 代表特定特徵類型的物件。 您可以為單一圖片要求多種特徵類型。
• type - 指定功能的列舉值。
• maxResults (選用) - 限制傳回結果的值。
• model (選用) - 如適用，您可以指定 builtin/stable (如果未設定，則為預設值) 或 builtin/latest，選擇模型。如需近期更新的型號清單，請參閱「版本資訊」主題。

傳送要求

您可以使用 curl 和 request.json 中的主體內容，將要求傳送至 Vision API。在指令列中輸入下列內容：

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" \
    https://vision.googleapis.com/v1/images:annotate -d @request.json

• 範例 curl 指令會使用 gcloud auth print-access-token 指令取得驗證權杖。
• 請注意，如要將檔案名稱傳送給 curl，請使用 -d 選項 (針對「資料」) 並在檔案名稱前加上 @ 符號。這個檔案的所在目錄應與您執行 curl 指令的所在目錄相同。

解讀回應

您應該會看到類似下方的 JSON 回應。

要求 JSON 主體為各個註解類型指定 maxResults。 因此，您會在回應 JSON 中看到以下內容：

• 三項 labelAnnotations 結果
• 一項 textAnnotations 結果 (為求清楚起見，已縮短)
• 一項 localizedObjectAnnotations 結果

回應

Note: Zero coordinate values omitted. When the API detects a coordinate ("x" or "y") value of 0, that coordinate is omitted in the JSON response. Thus, a response with a bounding poly around the entire image would be
[{},{"x": 100},{"x": 100,"y": 100},{"y": 100}] for an image that is 100 pixels by 100 pixels. For more information, see the API Reference documentation.

{
  "responses": [
    {
      "labelAnnotations": [
        {
          "mid": "/m/09g5pq",
          "description": "People",
          "score": 0.9504782,
          "topicality": 0.9504782
        },
        {
          "mid": "/m/01c8br",
          "description": "Street",
          "score": 0.8911568,
          "topicality": 0.8911568
        },
        {
          "mid": "/m/079bkr",
          "description": "Mode of transport",
          "score": 0.89089024,
          "topicality": 0.89089024
        }
      ],
      "textAnnotations": [
        {
          "locale": "zh",
          "description": "牛牛面馆\n",
          "boundingPoly": {
            "vertices": [
              {
                "x": 159,
                "y": 212
              },
              {
                "x": 947,
                "y": 212
              },
              {
                "x": 947,
                "y": 354
              },
              {
                "x": 159,
                "y": 354
              }
            ]
          }
        },
        ...
      ],
      "fullTextAnnotation": {
        "pages": [
          {
            ...
                "paragraphs": [
                  {
                    ...
                    "words": [
                      {
                        ...
                        "symbols": [
                          {
                            ...
                ],
                "blockType": "TEXT"
              }
            ]
          }
        ],
        "text": "牛牛面馆\n"
      },
      "localizedObjectAnnotations": [
        {
          "mid": "/m/01g317",
          "name": "Person",
          "score": 0.94413143,
          "boundingPoly": {
            "normalizedVertices": [
              {
                "x": 0.26063988,
                "y": 0.46869153
              },
              {
                "x": 0.40736017,
                "y": 0.46869153
              },
              {
                "x": 0.40736017,
                "y": 0.8957791
              },
              {
                "x": 0.26063988,
                "y": 0.8957791
              }
            ]
          }
        }
      ]
    }
  ]
}

標籤偵測結果

1. description: "人物", score: 0.950
2. description: "街道", score: 0.891
3. description: "交通工具", score: 0.890



圖片來源： Unsplash 的 Steve Long (已新增註解)。

文字偵測結果

• text: 牛牛面馆\n
• vertices: (x: 159, y: 212), (x: 947, y: 212), (x: 947, y: 354), (x: 159, y: 354 )



圖片來源： Unsplash 的 Steve Long (已新增註解)。

物件偵測結果

• name: "人", score: 0.944
• normalized vertices: (x: 0.260, y: 0.468), (x: 0.407, y: 0.468), (x: 0.407, y: 0.895), (x: 0.260, y: 0.895)



圖片來源： Unsplash 的 Steve Long (已新增註解)。

恭喜！您已將第一個要求傳送至 Vision API。

清除所用資源

如要避免系統向您的 Google Cloud 帳戶收取本頁面所用資源的費用，請刪除含有這些資源的 Google Cloud 專案。

Optional: Revoke credentials from the gcloud CLI.

gcloud auth revoke

後續步驟

• 請參閱所有特徵類型及其用途的清單。
• 使用 Vision API 用戶端程式庫，以您選擇的語言開始使用 Vision API。
• 如要進一步瞭解特定功能、查看註解範例，以及取得個別檔案或圖片的註解，請參閱操作指南。
• 瞭解如何批次註解圖片和檔案 (PDF/TIFF/GIF)。
• 瀏覽用戶端程式庫程式碼範例的完整清單。