Logo Recognition using Google Cloud Vision in Salesforce

In this post, I will explain logo detection using Google Cloud Vision API. I will try to integrate other APIs as well for logo detection in future posts.

Google Cloud Vision API can detect popular product logos within an image. We can detect logos by passing URL or base64-encoded-image. In Salesforce, we already have base64 data of images in ContentVersion object so we can easily pass that into the request body. For processing images using URL, we can use chatter feed URL for the image.

Let us go with step by step guide for integrating Google Cloud Vision API for logo detection. Below steps are required for API call

• Get Access Token from Google to call API
• Create Apex class to call API
• Create LWC Component to show brand

1. Get Access Token from Google to call API

Refer blog http://salesforcecodex.com/2020/02/integrating-google-api-with-salesforce/ to get access token for Google Cloud Vision API.

You need to enable Google Cloud Vision API for access token from https://console.cloud.google.com/apis/library/vision.googleapis.com. Use the below scope in GoogleAuthService class.

private static string scope='https://www.googleapis.com/auth/cloud-vision';

2. Create Apex class to call API

Let us create apex class to call Google Cloud Vision API. We have to use auth token generated from the above step. We have to get auth token from custom metadata GoogleAuthSetting__mdt before calling API. We are updating this metadata in the previous step after getting token.

API Detail

API Url : https://vision.googleapis.com/v1/images:annotate

Above API will be called as POST method. For this post, I am using blob image to get brand information. Sample JSON request data will be like this

{
  "requests": [
    {
      "image": {
        "content": "base64-encoded-image" //This will be content version data
      },
      "features": [
        {
          "type": "LOGO_DETECTION"  // type for logo detection
        },
      ]
    }
  ]
}

Response data will be like this.

{
  "responses": [
    {
      "logoAnnotations": [
        {
          "mid": "/m/045c7b",
          "description": "salesforce",
          "score": 0.980325,
          "boundingPoly": {
            "vertices": [
             ...........// index detail
            ]
          }
        }
      ]
    }
  ]
}