搜索产品

创建自己的商品集且将商品集编入索引后,可以使用 Cloud Vision API 查询商品集。

您可以将图片的 Google Cloud Storage URI、网址或 base64 编码字符串传递给 Cloud Vision API Product Search,从而找到与指定图片类似的商品。如需了解请求大小上限和配额信息,请参阅使用量限制

要查看有关检测单件商品以及检测图片中多件商品的示例,请参阅了解搜索响应和多件商品检测主题。

使用本地图片进行搜索

以下示例会读取一个本地文件,并通过在请求中内嵌原始图片字节(base64 编码图片)来查询 API。

REST 和命令行

在使用下面的任何请求数据之前,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。
  • project-id:您的 GCP 项目 ID。
  • location-id:有效的位置标识符。有效的位置标识符包括 us-west1us-east1europe-west1asia-east1
  • product-set-id:您要对其执行操作的商品集的 ID。

特定于字段的注意事项

  • features.maxResults - 要返回的结果数的上限。
  • imageContext.productCategories - 要搜索的商品类别。目前,您只能指定一种商品类别(家庭用品、服装、玩具、包装商品和一般商品)。
  • imageContext.filter - 用于商品标签的一个(或多个)键值对过滤表达式。格式:“key=value”。过滤键值对可以与 AND 或 OR 表达式搭配使用:“color=blue AND style=mens”或“color=blue OR color=black”。如果使用 OR 表达式,则表达式中的所有键必须相同

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": [
        {
          "type": "PRODUCT_SEARCH",
          "maxResults": 5
        }
      ],
      "imageContext": {
        "productSearchParams": {
          "productSet": "projects/project-id/locations/location-id/productSets/product-set-id",
          "productCategories": [
               "apparel"
          ],
          "filter": "style = womens"
        }
      }
    }
  ]
}

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 application-default print-access-token) \
-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 application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

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 JSON 包含以下两种结果类型:

  • productSearchResults - 包含整个图片的匹配商品列表。在示例响应中,匹配商品为 product_id65、product_id35、product_id34、product_id62 和 product_id32。
  • productGroupedResults - 包含图片中识别的每个商品的边界框坐标和匹配项。在以下响应中,仅识别了一个商品,后跟示例商品集中的匹配商品:product_id65、product_id35、product_id34、product_id93 和 product_id62。

请注意,虽然这两种结果类型存在重叠,但也可能存在差异(例如,响应中的 product_id32 和 product_id93)。

Go


import (
	"context"
	"fmt"
	"io"
	"os"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// getSimilarProducts searches for products from a product set similar to products in an image file.
func getSimilarProducts(w io.Writer, projectID string, location string, productSetID string, productCategory string, file string, filter string) error {
	ctx := context.Background()
	c, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return fmt.Errorf("NewImageAnnotatorClient: %v", err)
	}
	defer c.Close()

	f, err := os.Open(file)
	if err != nil {
		return fmt.Errorf("Open: %v", err)
	}
	defer f.Close()

	image, err := vision.NewImageFromReader(f)
	if err != nil {
		return fmt.Errorf("NewImageFromReader: %v", err)
	}

	ictx := &visionpb.ImageContext{
		ProductSearchParams: &visionpb.ProductSearchParams{
			ProductSet:        fmt.Sprintf("projects/%s/locations/%s/productSets/%s", projectID, location, productSetID),
			ProductCategories: []string{productCategory},
			Filter:            filter,
		},
	}

	response, err := c.ProductSearch(ctx, image, ictx)
	if err != nil {
		return fmt.Errorf("ProductSearch: %v", err)
	}

	fmt.Fprintf(w, "Product set index time:\n")
	fmt.Fprintf(w, "seconds: %d\n", response.IndexTime.Seconds)
	fmt.Fprintf(w, "nanos: %d\n", response.IndexTime.Nanos)

	fmt.Fprintf(w, "Search results:\n")
	for _, result := range response.Results {
		fmt.Fprintf(w, "Score(Confidence): %f\n", result.Score)
		fmt.Fprintf(w, "Image name: %s\n", result.Image)

		fmt.Fprintf(w, "Prodcut name: %s\n", result.Product.Name)
		fmt.Fprintf(w, "Product display name: %s\n", result.Product.DisplayName)
		fmt.Fprintf(w, "Product labels: %s\n", result.Product.ProductLabels)
	}

	return nil
}

Java

/**
 * Search similar products to image in local file.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productSetId - Id of the product set.
 * @param productCategory - Category of the product.
 * @param filePath - Local file path of the image to be searched
 * @param filter - Condition to be applied on the labels. Example for filter: (color = red OR
 *     color = blue) AND style = kids It will search on all products with the following labels:
 *     color:red AND style:kids color:blue AND style:kids
 * @throws IOException - on I/O errors.
 */
public static void getSimilarProductsFile(
    String projectId,
    String computeRegion,
    String productSetId,
    String productCategory,
    String filePath,
    String filter)
    throws IOException {
  try (ImageAnnotatorClient queryImageClient = ImageAnnotatorClient.create()) {

    // Get the full path of the product set.
    String productSetPath =
        ProductSearchClient.formatProductSetName(projectId, computeRegion, productSetId);

    // Read the image as a stream of bytes.
    File imgPath = new File(filePath);
    byte[] content = Files.readAllBytes(imgPath.toPath());

    // Create annotate image request along with product search feature.
    Feature featuresElement = Feature.newBuilder().setType(Type.PRODUCT_SEARCH).build();
    // The input image can be a HTTPS link or Raw image bytes.
    // Example:
    // To use HTTP link replace with below code
    //  ImageSource source = ImageSource.newBuilder().setImageUri(imageUri).build();
    //  Image image = Image.newBuilder().setSource(source).build();
    Image image = Image.newBuilder().setContent(ByteString.copyFrom(content)).build();
    ImageContext imageContext =
        ImageContext.newBuilder()
            .setProductSearchParams(
                ProductSearchParams.newBuilder()
                    .setProductSet(productSetPath)
                    .addProductCategories(productCategory)
                    .setFilter(filter))
            .build();

    AnnotateImageRequest annotateImageRequest =
        AnnotateImageRequest.newBuilder()
            .addFeatures(featuresElement)
            .setImage(image)
            .setImageContext(imageContext)
            .build();
    List<AnnotateImageRequest> requests = Arrays.asList(annotateImageRequest);

    // Search products similar to the image.
    BatchAnnotateImagesResponse response = queryImageClient.batchAnnotateImages(requests);

    List<Result> similarProducts =
        response.getResponses(0).getProductSearchResults().getResultsList();
    System.out.println("Similar Products: ");
    for (Result product : similarProducts) {
      System.out.println(String.format("\nProduct name: %s", product.getProduct().getName()));
      System.out.println(
          String.format("Product display name: %s", product.getProduct().getDisplayName()));
      System.out.println(
          String.format("Product description: %s", product.getProduct().getDescription()));
      System.out.println(String.format("Score(Confidence): %s", product.getScore()));
      System.out.println(String.format("Image name: %s", product.getImage()));
    }
  }
}

Node.js

// Imports the Google Cloud client library
const vision = require('@google-cloud/vision');
const fs = require('fs');
// Creates a client
const productSearchClient = new vision.ProductSearchClient();
const imageAnnotatorClient = new vision.ImageAnnotatorClient();

async function getSimilarProductsFile() {
  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'nodejs-docs-samples';
  // const location = 'us-west1';
  // const productSetId = 'indexed_product_set_id_for_testing';
  // const productCategory = 'apparel';
  // const filePath = './resources/shoes_1.jpg';
  // const filter = '';
  const productSetPath = productSearchClient.productSetPath(
    projectId,
    location,
    productSetId
  );
  const content = fs.readFileSync(filePath, 'base64');
  const request = {
    // The input image can be a GCS link or HTTPS link or Raw image bytes.
    // Example:
    // To use GCS link replace with below code
    // image: {source: {gcsImageUri: filePath}}
    // To use HTTP link replace with below code
    // image: {source: {imageUri: filePath}}
    image: {content: content},
    features: [{type: 'PRODUCT_SEARCH'}],
    imageContext: {
      productSearchParams: {
        productSet: productSetPath,
        productCategories: [productCategory],
        filter: filter,
      },
    },
  };
  const [response] = await imageAnnotatorClient.batchAnnotateImages({
    requests: [request],
  });
  console.log('Search Image:', filePath);
  const results = response['responses'][0]['productSearchResults']['results'];
  console.log('\nSimilar product information:');
  results.forEach(result => {
    console.log('Product id:', result['product'].name.split('/').pop(-1));
    console.log('Product display name:', result['product'].displayName);
    console.log('Product description:', result['product'].description);
    console.log('Product category:', result['product'].productCategory);
  });
}
getSimilarProductsFile();

Python

from google.cloud import vision

def get_similar_products_file(
        project_id, location, product_set_id, product_category,
        file_path, filter):
    """Search similar products to image.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_set_id: Id of the product set.
        product_category: Category of the product.
        file_path: Local file path of the image to be searched.
        filter: Condition to be applied on the labels.
        Example for filter: (color = red OR color = blue) AND style = kids
        It will search on all products with the following labels:
        color:red AND style:kids
        color:blue AND style:kids
    """
    # product_search_client is needed only for its helper methods.
    product_search_client = vision.ProductSearchClient()
    image_annotator_client = vision.ImageAnnotatorClient()

    # Read the image as a stream of bytes.
    with open(file_path, 'rb') as image_file:
        content = image_file.read()

    # Create annotate image request along with product search feature.
    image = vision.Image(content=content)

    # product search specific parameters
    product_set_path = product_search_client.product_set_path(
        project=project_id, location=location,
        product_set=product_set_id)
    product_search_params = vision.ProductSearchParams(
        product_set=product_set_path,
        product_categories=[product_category],
        filter=filter)
    image_context = vision.ImageContext(
        product_search_params=product_search_params)

    # Search products similar to the image.
    response = image_annotator_client.product_search(
        image, image_context=image_context)

    index_time = response.product_search_results.index_time
    print('Product set index time: ')
    print(index_time)

    results = response.product_search_results.results

    print('Search results:')
    for result in results:
        product = result.product

        print('Score(Confidence): {}'.format(result.score))
        print('Image name: {}'.format(result.image))

        print('Product name: {}'.format(product.name))
        print('Product display name: {}'.format(
            product.display_name))
        print('Product description: {}\n'.format(product.description))
        print('Product labels: {}\n'.format(product.product_labels))

使用远程图片进行搜索

您还可以选择通过指定给定图片的 Cloud Storage URI 来查找与该图片类似的商品。

REST 和命令行

在使用下面的任何请求数据之前,请先进行以下替换:

  • cloud-storage-image-uri:Cloud Storage 存储分区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://storage-bucket/filename.jpg
  • project-id:您的 GCP 项目 ID。
  • location-id:有效的位置标识符。有效的位置标识符包括 us-west1us-east1europe-west1asia-east1
  • product-set-id:您要对其执行操作的商品集的 ID。

特定于字段的注意事项

  • features.maxResults - 要返回的结果数的上限。
  • imageContext.productCategories - 要搜索的商品类别。目前,您只能指定一种商品类别(家庭用品、服装、玩具、包装商品和一般商品)。
  • imageContext.filter - 用于商品标签的一个(或多个)键值对过滤表达式。格式:“key=value”。过滤键值对可以与 AND 或 OR 表达式搭配使用:“color=blue AND style=mens”或“color=blue OR color=black”。如果使用 OR 表达式,则表达式中的所有键必须相同

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": [
        {
          "type": "PRODUCT_SEARCH",
          "maxResults": 5
        }
      ],
      "imageContext": {
        "productSearchParams": {
          "productSet": "projects/project-id/locations/location-id/productSets/product-set-id",
          "productCategories": [
               "apparel"
          ],
          "filter": "style = womens"
        }
      }
    }
  ]
}

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 application-default print-access-token) \
-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 application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

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 JSON 包含以下两种结果类型:

  • productSearchResults - 包含整个图片的匹配商品列表。在示例响应中,匹配商品为 product_id65、product_id35、product_id34、product_id62 和 product_id32。
  • productGroupedResults - 包含图片中识别的每个商品的边界框坐标和匹配项。在以下响应中,仅识别了一个商品,后跟示例商品集中的匹配商品:product_id65、product_id35、product_id34、product_id93 和 product_id62。

请注意,虽然这两种结果类型存在重叠,但也可能存在差异(例如,响应中的 product_id32 和 product_id93)。

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// getSimilarProductsURI searches for products from a product set similar to products in an image file on GCS.
func getSimilarProductsURI(w io.Writer, projectID string, location string, productSetID string, productCategory string, imageURI string, filter string) error {
	ctx := context.Background()
	c, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return fmt.Errorf("NewImageAnnotatorClient: %v", err)
	}
	defer c.Close()

	image := vision.NewImageFromURI(imageURI)

	ictx := &visionpb.ImageContext{
		ProductSearchParams: &visionpb.ProductSearchParams{
			ProductSet:        fmt.Sprintf("projects/%s/locations/%s/productSets/%s", projectID, location, productSetID),
			ProductCategories: []string{productCategory},
			Filter:            filter,
		},
	}

	response, err := c.ProductSearch(ctx, image, ictx)
	if err != nil {
		return fmt.Errorf("ProductSearch: %v", err)
	}

	fmt.Fprintf(w, "Product set index time:\n")
	fmt.Fprintf(w, "seconds: %d\n", response.IndexTime.Seconds)
	fmt.Fprintf(w, "nanos: %d\n", response.IndexTime.Nanos)

	fmt.Fprintf(w, "Search results:\n")
	for _, result := range response.Results {
		fmt.Fprintf(w, "Score(Confidence): %f\n", result.Score)
		fmt.Fprintf(w, "Image name: %s\n", result.Image)

		fmt.Fprintf(w, "Prodcut name: %s\n", result.Product.Name)
		fmt.Fprintf(w, "Product display name: %s\n", result.Product.DisplayName)
		fmt.Fprintf(w, "Product labels: %s\n", result.Product.ProductLabels)
	}

	return nil
}

Java

/**
 * Search similar products to image in Google Cloud Storage.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productSetId - Id of the product set.
 * @param productCategory - Category of the product.
 * @param gcsUri - GCS file path of the image to be searched
 * @param filter - Condition to be applied on the labels. Example for filter: (color = red OR
 *     color = blue) AND style = kids It will search on all products with the following labels:
 *     color:red AND style:kids color:blue AND style:kids
 * @throws Exception - on errors.
 */
public static void getSimilarProductsGcs(
    String projectId,
    String computeRegion,
    String productSetId,
    String productCategory,
    String gcsUri,
    String filter)
    throws Exception {
  try (ImageAnnotatorClient queryImageClient = ImageAnnotatorClient.create()) {

    // Get the full path of the product set.
    String productSetPath = ProductSetName.of(projectId, computeRegion, productSetId).toString();

    // Get the image from Google Cloud Storage
    ImageSource source = ImageSource.newBuilder().setGcsImageUri(gcsUri).build();

    // Create annotate image request along with product search feature.
    Feature featuresElement = Feature.newBuilder().setType(Type.PRODUCT_SEARCH).build();
    Image image = Image.newBuilder().setSource(source).build();
    ImageContext imageContext =
        ImageContext.newBuilder()
            .setProductSearchParams(
                ProductSearchParams.newBuilder()
                    .setProductSet(productSetPath)
                    .addProductCategories(productCategory)
                    .setFilter(filter))
            .build();

    AnnotateImageRequest annotateImageRequest =
        AnnotateImageRequest.newBuilder()
            .addFeatures(featuresElement)
            .setImage(image)
            .setImageContext(imageContext)
            .build();
    List<AnnotateImageRequest> requests = Arrays.asList(annotateImageRequest);

    // Search products similar to the image.
    BatchAnnotateImagesResponse response = queryImageClient.batchAnnotateImages(requests);

    List<Result> similarProducts =
        response.getResponses(0).getProductSearchResults().getResultsList();
    System.out.println("Similar Products: ");
    for (Result product : similarProducts) {
      System.out.println(String.format("\nProduct name: %s", product.getProduct().getName()));
      System.out.println(
          String.format("Product display name: %s", product.getProduct().getDisplayName()));
      System.out.println(
          String.format("Product description: %s", product.getProduct().getDescription()));
      System.out.println(String.format("Score(Confidence): %s", product.getScore()));
      System.out.println(String.format("Image name: %s", product.getImage()));
    }
  }
}

Node.js

// Imports the Google Cloud client library
const vision = require('@google-cloud/vision');
// Creates a client
const productSearchClient = new vision.ProductSearchClient();
const imageAnnotatorClient = new vision.ImageAnnotatorClient();

async function getSimilarProductsGcs(
  projectId,
  location,
  productSetId,
  productCategory,
  filePath,
  filter
) {
  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productSetId = 'Id of the product set';
  // const productCategory = 'Category of the product';
  // const filePath = 'Local file path of the image to be searched';
  // const filter = 'Condition to be applied on the labels';
  const productSetPath = productSearchClient.productSetPath(
    projectId,
    location,
    productSetId
  );

  const request = {
    // The input image can be a GCS link or HTTPS link or Raw image bytes.
    // Example:
    // To use GCS link replace with below code
    // image: {source: {gcsImageUri: filePath}}
    // To use HTTP link replace with below code
    // image: {source: {imageUri: filePath}}
    image: {source: {gcsImageUri: filePath}},
    features: [{type: 'PRODUCT_SEARCH'}],
    imageContext: {
      productSearchParams: {
        productSet: productSetPath,
        productCategories: [productCategory],
        filter: filter,
      },
    },
  };
  console.log(request.image);

  const [response] = await imageAnnotatorClient.batchAnnotateImages({
    requests: [request],
  });
  console.log('Search Image:', filePath);
  console.log('\nSimilar product information:');

  const results = response['responses'][0]['productSearchResults']['results'];
  results.forEach(result => {
    console.log('Product id:', result['product'].name.split('/').pop(-1));
    console.log('Product display name:', result['product'].displayName);
    console.log('Product description:', result['product'].description);
    console.log('Product category:', result['product'].productCategory);
  });
}
getSimilarProductsGcs();

Python

from google.cloud import vision

def get_similar_products_uri(
        project_id, location, product_set_id, product_category,
        image_uri, filter):
    """Search similar products to image.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_set_id: Id of the product set.
        product_category: Category of the product.
        image_uri: Cloud Storage location of image to be searched.
        filter: Condition to be applied on the labels.
        Example for filter: (color = red OR color = blue) AND style = kids
        It will search on all products with the following labels:
        color:red AND style:kids
        color:blue AND style:kids
    """
    # product_search_client is needed only for its helper methods.
    product_search_client = vision.ProductSearchClient()
    image_annotator_client = vision.ImageAnnotatorClient()

    # Create annotate image request along with product search feature.
    image_source = vision.ImageSource(image_uri=image_uri)
    image = vision.Image(source=image_source)

    # product search specific parameters
    product_set_path = product_search_client.product_set_path(
        project=project_id, location=location,
        product_set=product_set_id)
    product_search_params = vision.ProductSearchParams(
        product_set=product_set_path,
        product_categories=[product_category],
        filter=filter)
    image_context = vision.ImageContext(
        product_search_params=product_search_params)

    # Search products similar to the image.
    response = image_annotator_client.product_search(
        image, image_context=image_context)

    index_time = response.product_search_results.index_time
    print('Product set index time: ')
    print(index_time)

    results = response.product_search_results.results

    print('Search results:')
    for result in results:
        product = result.product

        print('Score(Confidence): {}'.format(result.score))
        print('Image name: {}'.format(result.image))

        print('Product name: {}'.format(product.name))
        print('Product display name: {}'.format(
            product.display_name))
        print('Product description: {}\n'.format(product.description))
        print('Product labels: {}\n'.format(product.product_labels))