Product Recognizer guide

The Product Recognizermodel helps you recognize and understand what products are in the provided image or on the shelf.

This model can serve as the primary AI building block for analyzing and interpreting product image data in retail stores. For example, you can use this model on shelf images that are captured by local cameras or mobile devices.

Tag Recognizer and Product Recognizer use cases

The Product Recognizer modeland the Tag Recognizer modelscan serve as the primary AI building blocks for analyzing and interpreting the image data around products and tags found in retail stores, such as the shelf scanning images captured by the installed cameras or mobile devices / platforms.

The Product recognizer and Tag recognizer models incorporate several core Google AI modeling and data capabilities to help the retailers and/or technical partners to solve key problems in understanding the retail shelf, including:

• Detecting, recognizing thus understanding what products are in the image or on the shelf.
• Detecting, recognizing, and parsing the tags (price-tag, for example, or any other text label tags) according to user defined key-value pair entity extraction schema.

In particular, several differentiating Google AI models are included in the shelf checking solution to support these use-cases problem solving, such as

• Product detection models (pre-trained by Google, but that you can still customize).
• Product thumbnail visual embedding model, which turns a product thumbnail image into a numerical feature space representation.
• Google OCR model, which extracts all texts visible in the image.
• Google entity extraction model (that you can customize), which turns the raw texts into the user defined key-value pair named entities.

In addition to these Google AI models, the shelf checking solution also leverages Google's large database of product information. The product data in this Product database includes the product's GTIN / UPC identity, product brand, title, and cross-language descriptions, product logo, and imagery with various packaging variations. The Product database with the previously mentioned product thumbnail visual embedding model enables the Product recognizer model to be able to recognize many products immediately.

For example, given a captured shelf image as follows, the shelf checking solution aims to:

1. Detect and localize all product item boxes (visible, not severely occluded) in the image, and recognize the product identity of each individual product item box at the GTIN / UPC level.
2. Detect and localize all tag boxes (visible) in the image, recognize all text strings in the tag, and then try to parse the text into the user-defined key-value pair entity extraction schema, such as product item description, price value.

The two major AI features to enable these solutions are Product Recognizer model and Tag Recognizer model, which we will provide more details in the following sections. For each of these two APIs that mainly provide the image inference services, there are one or more components in each API that you can customize. We will first describe the inference path of the API use, and then provide some short description of how the involved components you can customize, either through some user configuration or through some model training you carry out.

Product Recognizer functionality

This model recognizes individual product identity at the Global Trade Item Number (GTIN) level or the Universal Product Code (UPC) level. Several differentiating Google AI models are included in the Product Recognizer to empower these use-cases problem solving, such as:

• The product visual embedding model, which turns a product image into a numerical feature space representation.
• The Google OCR technology, which extracts all texts visible in the image.
• The Google product database used in combination with the product thumbnail visual embedding model enables the Product Recognizer model to recognize many products right away.

Example Output JSON Object

{
  "imageUri": " gs://test_bucket/test_image.jpg 
",
  "productRecognitionAnnotations": [
    {
      "detectedText": " Bolthouse Farms Perfectly Protein Tea & Soy Beverage 
",
      "recognitionResults": [
        {
          "confidence": 0.9420832 
,
          "productMetadata": {
            "brand": " Bolthouse Farms 
",
            "gtins": [
              " 00071464260804 
"
              ],
            "locale": " en-US 
",
            "title": " Bolthouse Farms Perfectly Protein Tea & Soy Beverage, Vanilla Chai Tea - 52 fl oz 
"
          },
        }
      ]
    }
  ]
}

API concepts

There are six API resources offered to help build product catalog, product dataset management, index building, and deployment for Product Recognition service. There are described as follows:

Catalog: Root resource which represents the container for all products offered by the retailer.

Product: Represents a product offered by a merchant. Product is a child resource of Catalog .

ProductImage: The image representing a view of one product. ProductImage is a child resource of Product .

ProductSet: A finer granularity container to organize and group products in the same Catalog . One ProductSet may contain one or many Product s but it does not "own" the containing Product s but instead maintains a "link" to them.

ProductRecognitionIndex: Contains a list of image embedding used for product recognition algorithms. ProductRecognitionIndex can be created either from the entire Catalog or from a ProductSet (a subset of the Product s from the Catalog ).

Endpoint: A placement that carries all the configurations required to perform Product Recognition or Tag Recognition inference. For Product Recognition, specifying product detection model and deploying a ProductRecognitionIndex are required. For Tag Recognition, specifying both tag detection and tag entity parsing models is required.

Environment setup

This section describes how to interact with Store Vision AI RESTful API.

   API_ENDPOINT 
 
 = 
 visionai 
 . 
 googleapis 
 . 
 com 
  PROJECT_ID 
 
 = 
 your 
 project 
 ID 
 

All the create methods require specifying the to-be-created resource name/ID explicitly. You may use a meaningful string identifier, for example, "product-ABC" or a randomly generated identifier for example, UUID.

To grant a person role the editor access to use Store Vision API, please run the following iam binding command:

 gcloud projects add-iam-policy-binding PROJECT_ID 
--member='user: USER_ACCOUNT 
' --role='roles/visionai.editor' 

To grant a service account the editor access, please use the below command:

 gcloud projects add-iam-policy-binding PROJECT_ID 
--member='serviceAccount: SERVICE_ACCOUNT 
' --role='roles/visionai.editor' 

Learn more about IAM binding .

Product Recognizer user journey

1. Create a Catalog.
2. Import Products and (optional) ProductImages into the Catalog .
3. View and modify the Product and ProductImages , and optionally creates a ProductSet to organize products list in a finer granularity.
4. Create an Index , either from the entire Catalog or from a ProductSet .
5. Create an Endpoint with desired product recognition config and deploys an Index to it.
6. Perform BatchAnalyze with ProductRecognition feature. In the backend, the system will identify products from each input image and retrieve top K similar products from the specified index using both visual and OCR text signals.

API resource management (Catalog and Indexset)

Catalog

Create Catalog

• CATALOG_ID =Your catalog id.

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" -d '{}' https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs?retail_catalog_id= CATALOG_ID 
 

Example output

 {
  "name": "projects/cloud-store-vision-test/locations/us-central1/operations/operation-1655157982362-5e15b7f95fa6f-d30364c6-dc3a3714",
  "done": false
} 

Pull Operation until done

• OPERATION_ID =Your output operation, for example, operation-1655157982362-5e15b7f95fa6f-d30364c6-dc3a3714

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/operations/ OPERATION_ID 
 

Example output

 {
  "name": "projects/cloud-store-vision-test/locations/us-central1/operations/operation-1655157982362-5e15b7f95fa6f-d30364c6-dc3a3714",
  "done": true
} 

ImportProduct

There are two supported import format:

• TXT: each line is the gtin of a Product to be imported
• JSONL: each line is a JSON format of RetailProductIoFormat, for example,

 {"retailProduct":{"name":"00040094314034","gtins":["00040094314034"]},"retailProductImages":[{"name":"1","gcsUri":"gs://shelfchecking-integration-test-data/products-data/00040094314034/1.jpg"}]}
{"retailProduct": {"name":"00123", "thirdPartyIds": {"id": "test-id", "owner": "test-owner"}}} 

Please see API reference for more details on RetailProductIoFormat. We currently support importing a maximum of 10,000 products per ImportProduct operation.

Please also note that the "name" within the "retailProductImages" only needs to be unique in the scope of parent "retailProduct" resource, meaning there could be 2 "retailProductImages" with the same "name" as long as they belong to different "retailProduct" resource.

• IMPORT_FILE_URI =Your import file Cloud Storage URI, for example, gs://mybucket/my_import_file.jsonl
• IMPORT_FORMAT =Your import file format, either FORMAT_JSONL or FORMAT_TXT

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
:importRetailProducts \
  -d '{
    "gcs_source": {
      "uris": " IMPORT_FILE_URI 
"
    },
    "format": " IMPORT_FORMAT 
"
  }' 

List Catalog

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs 

GetCatalog

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
 

DeleteCatalog

 curl -sS -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
 

Product

CreateProduct with GTIN

We support GTIN-8, GTIN-13, GTIN-14 and UPC(also known as GTIN-12) format. Learn more about GTIN format here .

• PRODUCT_ID =Your product id
• GTIN =gtin of your product, for example, 50735854797459, 00040094314034

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts?retail_product_id= PRODUCT_ID 
\
  -d '{"gtins": " GTIN 
"}' 

CreateProduct with Third-party ID

• PRODUCT_ID =Your product id
• THIRD_PARTY_ID =Third-party ID
• OWNER =The entity that owns the third party identifier

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts?retail_product_id= PRODUCT_ID 
\
-d '
  {
    "third_party_ids": {
      "id": " THIRD_PARTY_ID 
",
      "owner": " OWNER 
",
    }
  }' 

ListProducts

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts 

GetProducts

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
 

DeleteProduct

 curl -sS -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
 

ProductImage

CreateProductImage

• PRODUCT_IMAGE_ID =Your product image id
• IMAGE_GCS_URI =Your image Cloud Storage uri, for example, gs://mybucket/my_img.jpg

  curl 
  
 - 
 sS 
  
 - 
 X 
  
 POST 
  
 - 
 H 
  
 "Authorization: Bearer $(gcloud auth print-access-token)" 
  
 - 
 H 
  
 "Content-Type: application/json" 
  
 https 
 : 
 //visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
/retailProductImages?retail_product_image_id= PRODUCT_IMAGE_ID 
\ 
  
 - 
 d 
  
 ' 
 { 
  
 "source_type" 
 : 
  
 "SOURCE_TYPE_HAND_HELD_CAMERA" 
 , 
  
 "gcs_uri" 
 : 
  
 " IMAGE_GCS_URI 
" 
  
 } 
 ' 
 

ListProductImages

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
/retailProductImages 

GetProductImages

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
/retailProductImages/ PRODUCT_IMAGE_ID 
 

DeleteProductImage

 curl -sS -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProducts/ PRODUCT_ID 
/retailProductImages/ PRODUCT_IMAGE_ID 
 

ProductSet

CreateProductSet

• PRODUCT_SET_ID =Your product set id

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" -d '{}' https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets?retail_product_set_id= PRODUCT_SET_ID 
 

ListProductSet

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets 

GetProductSet

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets/ PRODUCT_SET_ID 
 

AddProductsToProductSet

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets/ PRODUCT_SET_ID 
:add \
  -d '{"product_ids": " PRODUCT_ID 
"}' 

RemoveProductsFromProductSet

 curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets/ PRODUCT_SET_ID 
:remove \
  -d '{"product_ids": " PRODUCT_ID 
"}' 

DeleteProductSet

 curl -sS -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductSets/ PRODUCT_SET_ID 
 

ProductRecognitionIndex

Create ProductRecognitionIndex

There are two ways to create a ProductRecognitionIndex, either from Catalog which will use all the everything contained in this Catalog, or from a ProductSet which will only use the associated products and product images.

• INDEX_ID =Your index id
• COVERAGE_CSV_OUTPUT_DIRECTORY =<Cloud Storage location of the directory where index coverage file will be written to

  # 
Create from Catalog
curl -sS -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductRecognitionIndexes?retail_product_recognition_index_id= INDEX_ID 
 

  # Create from Catalog and output index coverage CSV file to a Cloud Storage directory. 
 # This API method is especially useful when you want to understand the 
 # actual number of images used to construct the index per imported GTIN, and 
 # the image can be sourced from the Google Product database, your own importing, 
 # and other means (such as with the Google Data Labeling service. 
 curl 
  
 - 
 sS 
  
 - 
 X 
  
 POST 
  
 - 
 H 
  
 "Authorization: Bearer $(gcloud auth print-access-token)" 
  
 - 
 H 
  
 "Content-Type: application/json" 
  
 "https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductRecognitionIndexes?retail_product_recognition_index_id= INDEX_ID 
&coverage_output.output_uri_prefix= COVERAGE_CSV_OUTPUT_DIRECTORY 
" 
 

  # 
Create from ProductSet, by adding the following to the previous Curl command
-d '{"retail_product_set": "projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/' CATALOG_ID 
'/retailProductSets/ PRODUCT_SET_ID 
"}' 

Get ProductRecognitionIndex

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductRecognitionIndexes/ INDEX_ID 
 

List ProductRecognitionIndex

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductRecognitionIndexes 

Delete ProductRecognitionIndex

 curl -sS -X DELETE -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/ CATALOG_ID 
/retailProductRecognitionIndexes/ INDEX_ID 
 

Endpoint

Create Endpoint

• ENDPOINT_ID =Your endpoint id

  curl 
 - 
 sS 
 - 
 X 
 POST 
 - 
 H 
 "Authorization: Bearer $(gcloud auth print-access-token)" 
 - 
 H 
 "Content-Type: application/json" 
 https 
 : 
 // 
 visionai 
 . 
 googleapis 
 . 
 com 
 / 
 v1alpha1 
 / 
 projects 
 / 
  PROJECT_ID 
 
 / 
 locations 
 / 
 us 
 - 
 central1 
 / 
 retailEndpoints 
 ? 
 retail_endpoint_id 
 = 
  ENDPOINT_ID 
 
 - 
 d 
 ' 
 { 
 "productRecognitionConfig" 
 : 
 { 
 "recognitionConfidenceThreshold" 
 : 
 0.4 
 } 
 } 
 ' 
 

DeployProductRecognitionIndex

An Endpoint can only be deployed with one ProductRecognitionIndex, but one ProductRecognitionIndex can be deployed to multiple Endpoints.

  curl 
 - 
 sS 
 - 
 X 
 POST 
 - 
 H 
 "Authorization: Bearer $(gcloud auth print-access-token)" 
 - 
 H 
 "Content-Type: application/json" 
 https 
 : 
 // 
 visionai 
 . 
 googleapis 
 . 
 com 
 / 
 v1alpha1 
 / 
 projects 
 / 
  PROJECT_ID 
 
 / 
 locations 
 / 
 us 
 - 
 central1 
 / 
 retailEndpoints 
 / 
  ENDPOINT_ID 
 
 : 
 deployRetailProductRecognitionIndex 
 \ 
 - 
 d 
 ' 
 { 
 "retail_product_recognition_index" 
 : 
 "projects/ PROJECT_ID 
/locations/us-central1/retailCatalogs/' CATALOG_ID 
'/retailProductRecognitionIndexes/ INDEX_ID 
" 
 } 
 ' 
 

GetEndpoint

  curl 
 - 
 sS 
 - 
 X 
 GET 
 - 
 H 
 "Authorization: Bearer $(gcloud auth print-access-token)" 
 - 
 H 
 "Content-Type: application/json" 
 https 
 : 
 // 
 visionai 
 . 
 googleapis 
 . 
 com 
 / 
 v1alpha1 
 / 
 projects 
 / 
  PROJECT_ID 
 
 / 
 locations 
 / 
 us 
 - 
 central1 
 / 
 retailEndpoints 
 / 
  ENDPOINT_ID 
 
 

ListEndpoints

 curl -sS -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" -H "Content-Type: application/json" https://visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailEndpoints 

UndeployProductRecognitionIndex

Undeploy will only remove the deployed ProductRecognitionIndex from the current calling Endpoint, and will not affect other Endpoints if this ProductRecognitionIndex is also deployed to other ones.

  curl 
 - 
 sS 
 - 
 X 
 POST 
 - 
 H 
 "Authorization: Bearer $(gcloud auth print-access-token)" 
 - 
 H 
 "Content-Type: application/json" 
 https 
 : 
 // 
 visionai 
 . 
 googleapis 
 . 
 com 
 / 
 v1alpha1 
 / 
 projects 
 / 
  PROJECT_ID 
 
 / 
 locations 
 / 
 us 
 - 
 central1 
 / 
 retailEndpoints 
 / 
  ENDPOINT_ID 
 
 : 
 undeployRetailProductRecognitionIndex 
 

DeleteEndpoint

  curl 
 - 
 sS 
 - 
 X 
 DELETE 
 - 
 H 
 "Authorization: Bearer $(gcloud auth print-access-token)" 
 - 
 H 
 "Content-Type: application/json" 
 https 
 : 
 // 
 visionai 
 . 
 googleapis 
 . 
 com 
 / 
 v1alpha1 
 / 
 projects 
 / 
  PROJECT_ID 
 
 / 
 locations 
 / 
 us 
 - 
 central1 
 / 
 retailEndpoints 
 / 
  ENDPOINT_ID 
 
 

Batch Analyze Inference (Product Recognition)

Example input file at gs://my-bucket/input-file.csv :

 gs://my-bucket/my-image1.jpg
gs://my-bucket/my-image2.jpg
gs://my-bucket/my-image3.jpg 

• INPUT_FILE_URI =Cloud Storage uri of your input file> each line in the input file is just a Cloud Storage uri of image to process, for example, gs://my-bucket/my-image.jpg
• OUTPUT_URI_PREFIX =Cloud Storage uri prefix for output results file, for example, gs://my-bucket/my-output-dir

  curl 
  
 - 
 sS 
  
 - 
 X 
  
 POST 
  
 - 
 H 
  
 "Authorization: Bearer $(gcloud auth print-access-token)" 
  
 - 
 H 
  
 "Content-Type: application/json" 
  
 https 
 : 
 //visionai.googleapis.com/v1alpha1/projects/ PROJECT_ID 
/locations/us-central1/retailEndpoints/ ENDPOINT_ID 
:batchAnalyze -d '{ 
  
 "gcsSource" 
 : 
  
 { 
  
 "uris" 
 : 
  
 [ 
 " INPUT_FILE_URI 
" 
 ] 
  
 }, 
  
 "features" 
 : 
  
 [ 
  
 { 
  
 "type" 
 : 
  
 "TYPE_PRODUCT_RECOGNITION" 
 , 
  
 } 
  
 ], 
  
 "outputGcsDestination" 
 : 
  
 { 
  
 "outputUriPrefix" 
 : 
  
 " OUTPUT_URI_PREFIX 
" 
  
 } 
 } 
 ' 
 

  "features" 
 : 
  
 [ 
  
 { 
  
 "type" 
 : 
  
 "TYPE_PRODUCT_RECOGNITION" 
 , 
  
 "productRecognitionConfig" 
 : 
  
 { 
  
 "recognitionConfidenceThreshold" 
 : 
  
 0.4 
  
 } 
  
 } 
  
 ], 
 

There are also more fields that you can set and configure in the productRecognitionConfig , which is a RetailProductRecognitionConfig object. Please see the resource description in the API reference for more details.

API reference

Resource: projects.locations.retailCatalogs

JSON Representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "displayName" 
 : 
  
 string 
 , 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
 } 
 

Fields

Method: projects.locations.retailCatalogs.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/us-central1}/retailCatalogs

Path parameters

Request body

The request body contains an instance of RetailCatalog .

Response body

If successful, the response body contains a newly created instance of RetailCatalog .

Method: projects.locations.retailCatalogs.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/us-central1/retailCatalogs/*}

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailCatalog .

Method: projects.locations.retailCatalogs.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/us-central1}/retailCatalogs

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure: JSON representation

 {
  "retailCatalogs": [
    {
      object (RetailCatalog)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailCatalogs.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/us-central1/retailCatalogs/*}

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of Operation .

Method: projects.locations.retailCatalogs.importRetailProducts

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/us-central1/retailCatalogs/*}:importRetailProducts

Path parameters

Request body

JSON representation

  { 
  
 "gcsSource" 
 : 
  
 { 
  
 object 
 ( 
 GcsSource 
 ) 
  
 }, 
  
 "format" 
 : 
  
 enum 
 ( 
 Format 
 ) 
 } 
 

Fields

Format ENUM values

Response body

If successful, the response body contains an instance of Operation .

Resource: projects.locations.retailProducts

JSON Representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "gtins" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "normalizedGtins" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "thirdPartyIds" 
 : 
  
 [ 
 { object(ThirdPartyId) } 
 ] 
 , 
  
 "locale" 
 : 
  
 string 
 , 
  
 "brand" 
 : 
  
 string 
 , 
  
 "title" 
 : 
  
 string 
 , 
  
 "productUri" 
 : 
  
 string 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 } 
 

Fields

RetailThirdPartyId JSON Presentation

 {
  "id": string,
  "owner": string
} 

Fields

Method: projects.locations.retailCatalogs.retailProducts.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProducts

Path parameters

Request body

The request body contains an instance of RetailProduct .

Response body

If successful, the response body contains a newly created instance of RetailProduct .

Method: projects.locations.retailCatalogs.retailProducts.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProducts/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailProduct .

Method: projects.locations.retailCatalogs.retailProducts.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProducts

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure: JSON representation

 {
  "retailProducts": [
    {
      object (RetailProducts)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailCatalogs.retailProducts.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProducts/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body is empty.

Resource: projects.locations.retailProductImages

JSON Representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "displayName" 
 : 
  
 string 
 , 
  
 "sourceType" 
 : 
  
 enum 
 ( 
 SourceType 
 ), 
  
 "gcsUri" 
 : 
  
 string 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 } 
 

Fields

SourceType ENUM values

Method: projects.locations.retailCatalogs.retailProducts.retailProductImages.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*/retailProducts/*}/retailProductImages

Path parameters

Request body

The request body contains an instance of RetailProductImage .

Response body

If successful, the response body contains a newly created instance of RetailProductImage .

Method: projects.locations.retailCatalogs.retailProducts.retailProductImages.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProducts/*/retailProductImages/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailProductImage .

Method: projects.locations.retailCatalogs.retailProducts.retailProductImages.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*/retailProducts/*}/retailProductImages

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure:

JSON representation

 {
  "retailProductImages": [
    {
      object (RetailProductImages)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailCatalogs.retailProducts.retailProductImages.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProducts/*/retailProductImages/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body is empty.

Resource: projects.locations.retailCatalogs.retailProductSets

JSON representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "displayName" 
 : 
  
 string 
 , 
  
 "retailProductIds" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 } 
 

Fields

Method: projects.locations.retailCatalogs.retailProductSets.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProductSets

Path parameters

Request body

The request body contains an instance of RetailProductSet.

Response body

If successful, the response body contains a newly created instance of RetailProductSet.

Method: projects.locations.retailCatalogs.retailProductSets.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductSets/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailProductSet.

Method: projects.locations.retailCatalogs.retailProductSets.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProductSets

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure:

JSON representation

 {
  "retailProductSets": [
    {
      object (RetailProductSets)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailCatalogs.retailProductSets.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductSets/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body is empty.

Method: projects.locations.retailCatalogs.retailProductSets.add

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductSets/*}:remove

Path parameters

Request body

JSON representation

  { 
  
 "productIds" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "productFilter" 
 : 
  
 string 
 } 
 

Fields

Response body

If successful, the response body contains an instance of Operation .

Method: projects.locations.retailCatalogs.retailProductSets.remove

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductSets/*}:add

Path parameters

Request body

JSON representation

  { 
  
 "productIds" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "productFilter" 
 : 
  
 string 
 } 
 

Fields

Response body

If successful, the response body contains an instance of Operation .

Resource: projects.locations.retailCatalogs.retailProductRecognitionIndexes

JSON representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "displayName" 
 : 
  
 string 
 , 
  
 "description" 
 : 
  
 string 
 , 
  
 "retailProductSet" 
 : 
  
 [ 
 string 
 ] 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 } 
 

Fields

Method: projects.locations.retailCatalogs.retailProductRecognitionIndexes.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProductRecognitionIndexes

Path parameters

Request body

The request body contains an instance of RetailProductRecognitionIndex .

Response body

If successful, the response body contains a newly created instance of RetailProductRecognitionIndex .

Method: projects.locations.retailCatalogs.retailProductRecognitionIndexes.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductRecognitionIndexes/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailProductRecognitionIndex .

Method: projects.locations.retailCatalogs.retailProductRecognitionIndexes.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*/retailCatalogs/*}/retailProductRecognitionIndexes

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure:

JSON representation

 {
  "retailProductRecognitionIndexes": [
    {
      object (RetailProductRecognitionIndex)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailCatalogs.retailProductRecognitionIndexes.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailCatalogs/*/retailProductRecognitionIndexes/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of Operation .

Resource: projects.locations.retailEndpoints

JSON representation

  { 
  
 "name" 
 : 
  
 string 
 , 
  
 "displayName" 
 : 
  
 string 
 , 
  
 "description" 
 : 
  
 string 
 , 
  
 "deployedProductRecognitionIndex" 
 : 
  
 string 
 , 
  
 "resourceState" 
 : 
  
 enum 
 ( 
 RetailResourceState 
 ), 
  
 "productRecognitionConfig" 
 : 
  
 { 
  
 object 
 ( 
 RetailProductRecognitionConfig 
 ) 
  
 }, 
  
 "tagRecognitionConfig" 
 : 
  
 { 
  
 object 
 ( 
 RetailTagRecognitionConfig 
 ) 
  
 }, 
  
 "labels" 
 : 
  
 { 
  
 string 
 : 
  
 string 
 , 
  
 ... 
  
 } 
  
 "createTime" 
 : 
  
 string 
 , 
  
 "updateTime" 
 : 
  
 string 
 } 
 

Fields

RetailProductRecognitionConfig

JSON representation

 {
  "productDetectionModel": string,
  "detectionConfidenceThreshold": float,
  "recognitionConfidenceThreshold": float,
  "additionalConfig": { object }
} 

Fields

|

RetailTagRecognitionConfig

JSON representation

 {
  "tagDetectionModel": string,
  "tagParsingModel": string,
  "detectionConfidenceThreshold": float,
  "parsingConfidenceThreshold": float,
  "additionalConfig": { object }
} 

Fields

Method: projects.locations.retailEndpoints.create

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*}/retailEndpoints

Path parameters

Request body

The request body contains an instance of RetailEndpoint .

Response body

If successful, the response body contains a newly created instance of RetailEndpoint .

Method: projects.locations.retailEndpoints.get

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailEndpoints/*}

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of RetailEndpoint .

Method: projects.locations.retailEndpoints.list

HTTP request

GET https://visionai.googleapis.com/v1alpha1/{parent=projects/*/locations/*}/retailEndpoints

Path parameters

Query parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains data with the following structure:

JSON representation

 {
  "retailEndpoints": [
    {
      object (RetailEndpoint)
    }
  ],
  "nextPageToken": string
} 

Method: projects.locations.retailEndpoints.delete

HTTP request

DELETE https://visionai.googleapis.com/v1alpha1/{name=projects/*/locations/*/retailEndpoints/*

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body is empty.

Method: projects.locations.retailEndpoints.deployRetailProductRecognitionIndex

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{retailEndpoint=projects/*/locations/*/retailEndpoints/*}:deployRetailProductRecognitionIndex

Path parameters

Request body

JSON representation

 {
  "retailProductRecognitionIndex": string,
} 

Fields

Response body

If successful, the response body contains an instance of Operation .

Method: projects.locations.retailEndpoints.undeployRetailProductRecognitionIndex

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{retailEndpoint=projects/*/locations/*/retailEndpoints/*}:undeployRetailProductRecognitionIndex

Path parameters

Request body

The request body must be empty.

Response body

If successful, the response body contains an instance of Operation .

Method: projects.locations.retailEndpoints.batchAnalyze

HTTP request

POST https://visionai.googleapis.com/v1alpha1/{retailEndpoint=projects/*/locations/*/retailEndpoints/*}:batchAnalyze

Path parameters

Request body

JSON representation

  { 
  
 "gcsSource" 
 : 
  
 string 
 , 
  
 "features" 
 : 
  
 { 
  
 object 
 ( 
 Feature 
 ) 
  
 }, 
  
 // Union field output can be only one of the following: 
  
 "outputGcsDestination" 
 : 
  
 string 
 , 
  
 "corpus" 
 : 
  
 string 
 , 
  
 // End of list of possible types for union field output. 
  
 "bigqueryTable" 
 : 
  
 string 
 } 
 

Fields

Feature

JSON representation

  { 
  
 "type" 
 : 
  
 enum 
 ( 
 Type 
 ), 
  
 "productRecognitionConfig" 
 : 
  
 object 
 ( 
 RetailProductRecognitionConfig 
 ), 
  
 "tagRecognitionConfig" 
 : 
  
 object 
 ( 
 RetailTagRecognitionConfig 
 ) 
 } 
 

Fields

Response body

If successful, the response body contains an instance of Operation .

Types

GcsSource

JSON representation

  { 
  
 "uris" 
 : 
  
 [ 
 string 
 ] 
 } 
 

Fields

Type

ENUM values

RetailProductIoFormat

JSON representation

 {
  "retailProduct": { object(RetailProduct) },
  "retailProductImages": [ { object(RetailProductImage) }]
} 

Fields

RetailResourceState

ENUM values