检测网络实体和页面

Web 检测功能可检测对图片的 Web 引用。

狂欢节图片
图片来源:Quinten de Graaf (Unsplash)。

类别 响应
Web 实体
  • entityIdentityId:/m/02p7_j8,得分entityId:1.3225499,说明entityId:里约热内卢狂欢节
  • entityIdentityId:/m/06gmr,得分entityId:1.1684971,说明entityId:里约热内卢
  • entityIdentityId:/m/04cx88,得分entityId:1.05945,说明entityId:巴西狂欢节
...
完全匹配的图片
  • 网址url:https://1000lugaresparair.files.wordpress.com/2017/11/quinten-de-graaf-278848.jpg
  • 网址url:https://freewalkingtourrotterdam.com/wp-content/uploads/2017/07/quinten-de-graaf-278848.jpg
...
部分匹配的图片
  • 网址url:https://www.linnanneito.fi/wp-content/uploads/sambakarnevaali-riossa.jpg
  • 网址url:https://static.airhelp.com/wp-content/uploads/2019/02/26105557/two-women-in-carnival-costumes.jpg
...
具有匹配图片的页面
  • 网址url:https://travelnoire.com/best-carnival-celebrations-around-the-world/,
    pageTitleurl:Best \u003cb\u003eCarnival\u003c/b\u003e Celebrations Around The World - Travel Noire,
    fullMatchingImagesurl:[{网址url:https://travelnoire.com/wp-content/uploads/2019/02/quinten-de-graaf-278848-unsplash.jpg}]
  • 网址url:https://bespokebrazil.com/rio-carnival-2019/,
    pageTitleurl:Visit \u003cb\u003eRio Carnival 2019\u003c/b\u003e with the Brazil Specialists - Bespoke Brazil,
    partialMatchingImagesurl:[{网址url:https://bespoke-brazil-2018-bespokebrazil.netdna-ssl.com/wp-content/uploads/2019/01/Carnival-1.jpg}]
...
外观类似的图片
  • 网址url:https://www.brazilbookers.com/_images/photos/rio-carnival-images/rio-carnival-2016-carnival-date.jpg
  • 网址url:https://image.redbull.com/rbcom/010/2017-02-08/1331843859949_3/0100/0/1/watch-rio-carnival-2017-live-on-red-bull-tv.jpg
...
最佳猜测标签 2019 年里约狂欢节舞者

Web 检测请求

设置您的 Google Cloud 项目和身份验证

使用本地图片检测 Web 实体

您可以使用 Vision API 对本地图片文件执行特征检测。

对于 REST 请求,请将图片文件的内容作为 base64 编码的字符串在请求正文中发送。

对于 gcloud 和客户端库请求,请在请求中指定本地图片的路径。

REST

在使用任何请求数据之前,请先进行以下替换:

  • BASE64_ENCODED_IMAGE:二进制图片数据的 base64 表示(ASCII 字符串)。此字符串应类似于以下字符串:
    • /9j/4QAYRXhpZgAA...9tAVx/zDQDlGxn//2Q==
    如需了解详情,请参阅 base64 编码主题。
  • RESULTS_INT:(可选)要返回的结果的整数值。如果您省略 "maxResults" 字段及其值,则 API 会默认返回 10 个结果。此字段不适用于以下功能类型:TEXT_DETECTIONDOCUMENT_TEXT_DETECTIONCROP_HINTS
  • PROJECT_ID:您的 Google Cloud 项目 ID。

HTTP 方法和网址:

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

请求 JSON 正文:

{
  "requests": [
    {
      "image": {
        "content": "BASE64_ENCODED_IMAGE"
      },
      "features": [
        {
          "maxResults": RESULTS_INT,
          "type": "WEB_DETECTION"
        },
      ]
    }
  ]
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

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

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$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

如果请求成功,服务器将返回一个 200 OK HTTP 状态代码以及 JSON 格式的响应。

响应

Go

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Go 设置说明进行操作。 如需了解详情,请参阅 Vision Go API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


// detectWeb gets image properties from the Vision API for an image at the given file path.
func detectWeb(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
	}
	web, err := client.DetectWeb(ctx, image, nil)
	if err != nil {
		return err
	}

	fmt.Fprintln(w, "Web properties:")
	if len(web.FullMatchingImages) != 0 {
		fmt.Fprintln(w, "\tFull image matches:")
		for _, full := range web.FullMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", full.Url)
		}
	}
	if len(web.PagesWithMatchingImages) != 0 {
		fmt.Fprintln(w, "\tPages with this image:")
		for _, page := range web.PagesWithMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", page.Url)
		}
	}
	if len(web.WebEntities) != 0 {
		fmt.Fprintln(w, "\tEntities:")
		fmt.Fprintln(w, "\t\tEntity\t\tScore\tDescription")
		for _, entity := range web.WebEntities {
			fmt.Fprintf(w, "\t\t%-14s\t%-2.4f\t%s\n", entity.EntityId, entity.Score, entity.Description)
		}
	}
	if len(web.BestGuessLabels) != 0 {
		fmt.Fprintln(w, "\tBest guess labels:")
		for _, label := range web.BestGuessLabels {
			fmt.Fprintf(w, "\t\t%s\n", label.Label)
		}
	}

	return nil
}

Java

在试用此示例之前,请按照Vision API 快速入门:使用客户端库中的 Java 设置说明进行操作。如需了解详情,请参阅 Vision API Java 参考文档


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.WebDetection;
import com.google.cloud.vision.v1.WebDetection.WebEntity;
import com.google.cloud.vision.v1.WebDetection.WebImage;
import com.google.cloud.vision.v1.WebDetection.WebLabel;
import com.google.cloud.vision.v1.WebDetection.WebPage;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectWebDetections {

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

  // Finds references to the specified image on the web.
  public static void detectWebDetections(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(Type.WEB_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;
        }

        // Search the web for usages of the image. You could use these signals later
        // for user input moderation or linking external references.
        // For a full list of available annotations, see http://g.co/cloud/vision/docs
        WebDetection annotation = res.getWebDetection();
        System.out.println("Entity:Id:Score");
        System.out.println("===============");
        for (WebEntity entity : annotation.getWebEntitiesList()) {
          System.out.println(
              entity.getDescription() + " : " + entity.getEntityId() + " : " + entity.getScore());
        }
        for (WebLabel label : annotation.getBestGuessLabelsList()) {
          System.out.format("%nBest guess label: %s", label.getLabel());
        }
        System.out.println("%nPages with matching images: Score%n==");
        for (WebPage page : annotation.getPagesWithMatchingImagesList()) {
          System.out.println(page.getUrl() + " : " + page.getScore());
        }
        System.out.println("%nPages with partially matching images: Score%n==");
        for (WebImage image : annotation.getPartialMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with fully matching images: Score%n==");
        for (WebImage image : annotation.getFullMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with visually similar images: Score%n==");
        for (WebImage image : annotation.getVisuallySimilarImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
      }
    }
  }
}

Node.js

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Node.js 设置说明进行操作。 如需了解详情,请参阅 Vision Node.js API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


// Imports the Google Cloud client library
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';

// Detect similar images on the web to a local file
const [result] = await client.webDetection(fileName);
const webDetection = result.webDetection;
if (webDetection.fullMatchingImages.length) {
  console.log(
    `Full matches found: ${webDetection.fullMatchingImages.length}`
  );
  webDetection.fullMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.partialMatchingImages.length) {
  console.log(
    `Partial matches found: ${webDetection.partialMatchingImages.length}`
  );
  webDetection.partialMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.webEntities.length) {
  console.log(`Web entities found: ${webDetection.webEntities.length}`);
  webDetection.webEntities.forEach(webEntity => {
    console.log(`  Description: ${webEntity.description}`);
    console.log(`  Score: ${webEntity.score}`);
  });
}

if (webDetection.bestGuessLabels.length) {
  console.log(
    `Best guess labels found: ${webDetection.bestGuessLabels.length}`
  );
  webDetection.bestGuessLabels.forEach(label => {
    console.log(`  Label: ${label.label}`);
  });
}

Python

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Python 设置说明进行操作。 如需了解详情,请参阅 Vision Python API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

def detect_web(path):
    """Detects web annotations given an image."""
    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.web_detection(image=image)
    annotations = response.web_detection

    if annotations.best_guess_labels:
        for label in annotations.best_guess_labels:
            print(f"\nBest guess label: {label.label}")

    if annotations.pages_with_matching_images:
        print(
            "\n{} Pages with matching images found:".format(
                len(annotations.pages_with_matching_images)
            )
        )

        for page in annotations.pages_with_matching_images:
            print(f"\n\tPage url   : {page.url}")

            if page.full_matching_images:
                print(
                    "\t{} Full Matches found: ".format(len(page.full_matching_images))
                )

                for image in page.full_matching_images:
                    print(f"\t\tImage url  : {image.url}")

            if page.partial_matching_images:
                print(
                    "\t{} Partial Matches found: ".format(
                        len(page.partial_matching_images)
                    )
                )

                for image in page.partial_matching_images:
                    print(f"\t\tImage url  : {image.url}")

    if annotations.web_entities:
        print("\n{} Web entities found: ".format(len(annotations.web_entities)))

        for entity in annotations.web_entities:
            print(f"\n\tScore      : {entity.score}")
            print(f"\tDescription: {entity.description}")

    if annotations.visually_similar_images:
        print(
            "\n{} visually similar images found:\n".format(
                len(annotations.visually_similar_images)
            )
        )

        for image in annotations.visually_similar_images:
            print(f"\tImage url    : {image.url}")

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

其他语言

C#: 请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 版 Vision 参考文档。

PHP: 请按照客户端库页面上的 PHP 设置说明操作,然后访问 PHP 版 Vision 参考文档。

Ruby 版: 请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 版 Vision 参考文档。

使用远程图片检测 Web 实体

您可以使用 Vision API 对位于 Cloud Storage 或网络中的远程图片文件执行特征检测。如需发送远程文件请求,请在请求正文中指定文件的网址或 Cloud Storage URI。

REST

在使用任何请求数据之前,请先进行以下替换:

  • CLOUD_STORAGE_IMAGE_URI:Cloud Storage 存储桶中有效图片文件的路径。您必须至少拥有该文件的读取权限。 示例:
    • gs://cloud-samples-data/vision/web/carnaval.jpeg
  • RESULTS_INT:(可选)要返回的结果的整数值。如果您省略 "maxResults" 字段及其值,则 API 会默认返回 10 个结果。此字段不适用于以下功能类型:TEXT_DETECTIONDOCUMENT_TEXT_DETECTIONCROP_HINTS
  • PROJECT_ID:您的 Google Cloud 项目 ID。

HTTP 方法和网址:

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

请求 JSON 正文:

{
  "requests": [
    {
      "image": {
        "source": {
          "gcsImageUri": "CLOUD_STORAGE_IMAGE_URI"
        }
      },
      "features": [
        {
          "maxResults": RESULTS_INT,
          "type": "WEB_DETECTION"
        },
      ]
    }
  ]
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

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

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$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

如果请求成功,服务器将返回一个 200 OK HTTP 状态代码以及 JSON 格式的响应。

响应

Go

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Go 设置说明进行操作。 如需了解详情,请参阅 Vision Go API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


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

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

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

	fmt.Fprintln(w, "Web properties:")
	if len(web.FullMatchingImages) != 0 {
		fmt.Fprintln(w, "\tFull image matches:")
		for _, full := range web.FullMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", full.Url)
		}
	}
	if len(web.PagesWithMatchingImages) != 0 {
		fmt.Fprintln(w, "\tPages with this image:")
		for _, page := range web.PagesWithMatchingImages {
			fmt.Fprintf(w, "\t\t%s\n", page.Url)
		}
	}
	if len(web.WebEntities) != 0 {
		fmt.Fprintln(w, "\tEntities:")
		fmt.Fprintln(w, "\t\tEntity\t\tScore\tDescription")
		for _, entity := range web.WebEntities {
			fmt.Fprintf(w, "\t\t%-14s\t%-2.4f\t%s\n", entity.EntityId, entity.Score, entity.Description)
		}
	}
	if len(web.BestGuessLabels) != 0 {
		fmt.Fprintln(w, "\tBest guess labels:")
		for _, label := range web.BestGuessLabels {
			fmt.Fprintf(w, "\t\t%s\n", label.Label)
		}
	}

	return nil
}

Java

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Java 设置说明进行操作。 如需了解详情,请参阅 Vision Java API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


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.ImageSource;
import com.google.cloud.vision.v1.WebDetection;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class DetectWebDetectionsGcs {

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

  // Detects whether the remote image on Google Cloud Storage has features you would want to
  // moderate.
  public static void detectWebDetectionsGcs(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(Feature.Type.WEB_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;
        }

        // Search the web for usages of the image. You could use these signals later
        // for user input moderation or linking external references.
        // For a full list of available annotations, see http://g.co/cloud/vision/docs
        WebDetection annotation = res.getWebDetection();
        System.out.println("Entity:Id:Score");
        System.out.println("===============");
        for (WebDetection.WebEntity entity : annotation.getWebEntitiesList()) {
          System.out.println(
              entity.getDescription() + " : " + entity.getEntityId() + " : " + entity.getScore());
        }
        for (WebDetection.WebLabel label : annotation.getBestGuessLabelsList()) {
          System.out.format("%nBest guess label: %s", label.getLabel());
        }
        System.out.println("%nPages with matching images: Score%n==");
        for (WebDetection.WebPage page : annotation.getPagesWithMatchingImagesList()) {
          System.out.println(page.getUrl() + " : " + page.getScore());
        }
        System.out.println("%nPages with partially matching images: Score%n==");
        for (WebDetection.WebImage image : annotation.getPartialMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with fully matching images: Score%n==");
        for (WebDetection.WebImage image : annotation.getFullMatchingImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
        System.out.println("%nPages with visually similar images: Score%n==");
        for (WebDetection.WebImage image : annotation.getVisuallySimilarImagesList()) {
          System.out.println(image.getUrl() + " : " + image.getScore());
        }
      }
    }
  }
}

Node.js

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Node.js 设置说明进行操作。 如需了解详情,请参阅 Vision Node.js API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证


// 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';

// Detect similar images on the web to a remote file
const [result] = await client.webDetection(`gs://${bucketName}/${fileName}`);
const webDetection = result.webDetection;
if (webDetection.fullMatchingImages.length) {
  console.log(
    `Full matches found: ${webDetection.fullMatchingImages.length}`
  );
  webDetection.fullMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.partialMatchingImages.length) {
  console.log(
    `Partial matches found: ${webDetection.partialMatchingImages.length}`
  );
  webDetection.partialMatchingImages.forEach(image => {
    console.log(`  URL: ${image.url}`);
    console.log(`  Score: ${image.score}`);
  });
}

if (webDetection.webEntities.length) {
  console.log(`Web entities found: ${webDetection.webEntities.length}`);
  webDetection.webEntities.forEach(webEntity => {
    console.log(`  Description: ${webEntity.description}`);
    console.log(`  Score: ${webEntity.score}`);
  });
}

if (webDetection.bestGuessLabels.length) {
  console.log(
    `Best guess labels found: ${webDetection.bestGuessLabels.length}`
  );
  webDetection.bestGuessLabels.forEach(label => {
    console.log(`  Label: ${label.label}`);
  });
}

Python

试用此示例之前,请按照《Vision 快速入门:使用客户端库》中的 Python 设置说明进行操作。 如需了解详情,请参阅 Vision Python API 参考文档

如需向 Vision 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

def detect_web_uri(uri):
    """Detects web annotations in the file located in Google Cloud Storage."""
    from google.cloud import vision

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

    response = client.web_detection(image=image)
    annotations = response.web_detection

    if annotations.best_guess_labels:
        for label in annotations.best_guess_labels:
            print(f"\nBest guess label: {label.label}")

    if annotations.pages_with_matching_images:
        print(
            "\n{} Pages with matching images found:".format(
                len(annotations.pages_with_matching_images)
            )
        )

        for page in annotations.pages_with_matching_images:
            print(f"\n\tPage url   : {page.url}")

            if page.full_matching_images:
                print(
                    "\t{} Full Matches found: ".format(len(page.full_matching_images))
                )

                for image in page.full_matching_images:
                    print(f"\t\tImage url  : {image.url}")

            if page.partial_matching_images:
                print(
                    "\t{} Partial Matches found: ".format(
                        len(page.partial_matching_images)
                    )
                )

                for image in page.partial_matching_images:
                    print(f"\t\tImage url  : {image.url}")

    if annotations.web_entities:
        print("\n{} Web entities found: ".format(len(annotations.web_entities)))

        for entity in annotations.web_entities:
            print(f"\n\tScore      : {entity.score}")
            print(f"\tDescription: {entity.description}")

    if annotations.visually_similar_images:
        print(
            "\n{} visually similar images found:\n".format(
                len(annotations.visually_similar_images)
            )
        )

        for image in annotations.visually_similar_images:
            print(f"\tImage url    : {image.url}")

    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

如需执行 Web 检测,请使用 gcloud ml vision detect-web 命令,如以下示例所示:

gcloud ml vision detect-web gs://cloud-samples-data/vision/web/carnaval.jpeg

其他语言

C#: 请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 版 Vision 参考文档。

PHP: 请按照客户端库页面上的 PHP 设置说明操作,然后访问 PHP 版 Vision 参考文档。

Ruby 版: 请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 版 Vision 参考文档。

试用

在下面尝试检测 Web 实体。您可以使用已指定的图片 (gs://cloud-samples-data/vision/web/carnaval.jpeg) 或指定您自己的图片。选择执行即可发送请求。

狂欢节图片
图片来源:Quinten de Graaf (Unsplash)。

请求正文:

{
  "requests": [
    {
      "features": [
        {
          "type": "WEB_DETECTION"
        }
      ],
      "image": {
        "source": {
          "gcsImageUri": "gs://cloud-samples-data/vision/web/carnaval.jpeg"
        }
      }
    }
  ]
}