Merge pull request #249174 from ginalee-dotcom/ginalee-dotcom-patch-1

prmerger-automator[bot] · web-flow · commit 6e9d994bb49c · 2023-08-30T22:12:16.000Z
Update shelf docs
diff --git a/articles/ai-services/computer-vision/concept-shelf-analysis.md b/articles/ai-services/computer-vision/concept-shelf-analysis.md
@@ -30,13 +30,13 @@ Try out the capabilities of Product Recognition quickly and easily in your brows
 
 ## Product Recognition features
 
-### Image modification
+### Shelf Image Composition
 
 The [stitching and rectification APIs](./how-to/shelf-modify-images.md) let you modify images to improve the accuracy of the Product Understanding results. You can use these APIs to:
 * Stitch together multiple images of a shelf to create a single image.
 * Rectify an image to remove perspective distortion.
 
-### Product Understanding (pretrained)
+### Shelf Product Recognition (pretrained model)
 
 The [Product Understanding API](./how-to/shelf-analyze.md) lets you analyze a shelf image using the out-of-box pretrained model. This operation detects products and gaps in the shelf image and returns the bounding box coordinates of each product and gap, along with a confidence score for each.
 
@@ -85,7 +85,7 @@ The following JSON response illustrates what the Product Understanding API retur
 }
 ```
 
-### Product Understanding (custom)
+### Shelf Product Recognition - Custom (customized model)
 
 The Product Understanding API can also be used with a [custom trained model](./how-to/shelf-model-customization.md) to detect your specific products. This operation returns the bounding box coordinates of each product and gap, along with the label of each product.
 
@@ -134,7 +134,7 @@ The following JSON response illustrates what the Product Understanding API retur
 }
 ```
 
-### Planogram matching
+### Shelf Planogram Compliance (preview)
 
 The [Planogram matching API](./how-to/shelf-planogram.md) lets you compare the results of the Product Understanding API to a planogram document. This operation matches each detected product and gap to its corresponding position in the planogram document.
 
diff --git a/articles/ai-services/computer-vision/how-to/shelf-analyze.md b/articles/ai-services/computer-vision/how-to/shelf-analyze.md
@@ -12,7 +12,7 @@ ms.author: pafarley
 ms.custom: references_regions, build-2023, build-2023-dataai
 ---
 
-# Analyze a shelf image using pretrained models
+# Shelf Product Recognition (preview): Analyze shelf images using pretrained model
 
 The fastest way to start using Product Recognition is to use the built-in pretrained AI models. With the Product Understanding API, you can upload a shelf image and get the locations of products and gaps.
 
@@ -37,13 +37,14 @@ To analyze a shelf image, do the following steps:
 1. Copy the following `curl` command into a text editor.
 
     ```bash
-    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/vision/v4.0-preview.1/operations/shelfanalysis-productunderstanding:analyze" -d "{
+    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/computervision/productrecognition/ms-pretrained-product-detection/runs/<your_run_name>?api-version=2023-04-01-preview" -d "{
         'url':'<your_url_string>'
     }"
     ```
 1. Make the following changes in the command where needed:
-    1. Replace the value of `<subscriptionKey>` with your Vision resource key.
-    1. Replace the value of `<endpoint>` with your Vision resource endpoint. For example: `https://YourResourceName.cognitiveservices.azure.com`.
+    1. Replace the `<subscriptionKey>` with your Vision resource key.
+    1. Replace the `<endpoint>` with your Vision resource endpoint. For example: `https://YourResourceName.cognitiveservices.azure.com`.
+    2. Replace the `<your_run_name>` with your unique test run name for the task queue. It is an async API task queue name for you to be able retrieve the API response later. For example, `.../runs/test1?api-version...`
     1. Replace the `<your_url_string>` contents with the blob URL of the image
 1. Open a command prompt window.
 1. Paste your edited `curl` command from the text editor into the command prompt window, and then run the command.
diff --git a/articles/ai-services/computer-vision/how-to/shelf-model-customization.md b/articles/ai-services/computer-vision/how-to/shelf-model-customization.md
@@ -13,7 +13,7 @@ ms.date: 05/02/2023
 ms.author: pafarley
 ---
 
-# Train a custom Product Recognition model
+# Shelf Product Recognition - Custom Model (preview)
 
 You can train a custom model to recognize specific retail products for use in a Product Recognition scenario. The out-of-box [Analyze](shelf-analyze.md) operation doesn't differentiate between products, but you can build this capability into your app through custom labeling and training.
 
@@ -47,11 +47,20 @@ When your custom model is trained and ready (you've completed the steps in the [
 The API call will look like this:
 
 ```bash
-curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/vision/v4.0-preview.1/operations/shelfanalysis-productunderstanding:analyze?PRODUCT_CLASSIFIER_MODEL=myModelName" -d "{
+curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/computervision/productrecognition/ms-pretrained-product-detection/models/<your_model_name>/runs/<your_run_name>?api-version=2023-04-01-preview" -d "{
     'url':'<your_url_string>'
 }"
 ```
 
+1. Make the following changes in the command where needed:
+    1. Replace the `<subscriptionKey>` with your Vision resource key.
+    1. Replace the `<endpoint>` with your Vision resource endpoint. For example: `https://YourResourceName.cognitiveservices.azure.com`.
+    1. Replace the `<your_model_name>` with your unique custom model name. This will be the name of the customized model you have trained with your own data. For example, `.../models/mymodel1/runs/...`
+    2. Replace the `<your_run_name>` with your unique test run name for the task queue. It is an async API task queue name for you to be able retrieve the API response later. For example, `.../runs/test1?api-version...`
+    1. Replace the `<your_url_string>` contents with the blob URL of the image
+1. Open a command prompt window.
+1. Paste your edited `curl` command from the text editor into the command prompt window, and then run the command.
+
 ## Next steps
 
 In this guide, you learned how to use a custom Product Recognition model to better meet your business needs. Next, set up planogram matching, which works in conjunction with custom Product Recognition.
diff --git a/articles/ai-services/computer-vision/how-to/shelf-modify-images.md b/articles/ai-services/computer-vision/how-to/shelf-modify-images.md
@@ -12,13 +12,13 @@ ms.author: ginle
 ms.custom: references_regions, build-2023
 ---
 
-# Prepare images for Product Recognition
+# Shelf Image Composition (preview)
 
 Part of the Product Recognition workflow involves fixing and modifying the input images so the service can perform correctly. 
 
-This guide shows you how to use the Stitching API to combine multiple images of the same physical shelf: this gives you a composite image of the entire retail shelf, even if it's only viewed partially by multiple different cameras.
+This guide shows you how to use the **Stitching API** to combine multiple images of the same physical shelf: this gives you a composite image of the entire retail shelf, even if it's only viewed partially by multiple different cameras.
 
-This guide also shows you how to use the Rectification API to correct for perspective distortion when you stitch together different images.
+This guide also shows you how to use the **Rectification API** to correct for perspective distortion when you stitch together different images.
 
 ## Prerequisites
 * An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services/) 
@@ -44,7 +44,7 @@ To run the image stitching operation on a set of images, follow these steps:
 1. Copy the following `curl` command into a text editor.
 
     ```bash
-    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "<endpoint>/computervision/imagecomposition:stitch?api-version=2023-04-01-preview" --output <your_filename> -d "{
+    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/computervision/imagecomposition:stitch?api-version=2023-04-01-preview" --output <your_filename> -d "{
         'images': [
             {
             'url':'<your_url_string>'
@@ -83,7 +83,7 @@ To correct the perspective distortion in the composite image, follow these steps
 1. Copy the following `curl` command into a text editor.
 
     ```bash
-    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "<endpoint>/computervision/imagecomposition:rectify?api-version=2023-04-01-preview" --output <your_filename> -d "{
+    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/computervision/imagecomposition:rectify?api-version=2023-04-01-preview" --output <your_filename> -d "{
       'url': '<your_url_string>',
       'controlPoints': {
         'topLeft': {
diff --git a/articles/ai-services/computer-vision/how-to/shelf-planogram.md b/articles/ai-services/computer-vision/how-to/shelf-planogram.md
@@ -12,9 +12,9 @@ ms.date: 05/02/2023
 ms.author: pafarley
 ---
 
-# Check planogram compliance with Image Analysis
+# Shelf Planogram Compliance (preview)
 
-A planogram is a diagram that indicates the correct placement of retail products on shelves. The Image Analysis Planogram Matching API lets you compare analysis results from a photo to the store's planogram input. It returns an account of all the positions in the planogram, and whether a product was found in each position.
+A planogram is a diagram that indicates the correct placement of retail products on shelves. The Planogram Compliance API lets you compare analysis results from a photo to the store's planogram input. It returns an account of all the positions in the planogram, and whether a product was found in each position.
 
 :::image type="content" source="../media/shelf/planogram.png" alt-text="Photo of a retail shelf with detected products outlined and planogram position rectangles outlined separately.":::
 
@@ -251,7 +251,7 @@ This is the text you'll use in your API request body.
 1. Copy the following `curl` command into a text editor.
 
     ```bash
-    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/vision/v4.0-preview.1/operations/shelfanalysis-planogrammatching:analyze" -d "<body>"
+    curl.exe -H "Ocp-Apim-Subscription-Key: <subscriptionKey>" -H "Content-Type: application/json" "https://<endpoint>/computervision/planogramcompliance:match?api-version=2023-04-01-preview" -d "<body>"
     ```
 1. Make the following changes in the command where needed:
     1. Replace the value of `<subscriptionKey>` with your Vision resource key.
