Amazon Rekognition

With Amazon Rekognition, you can quickly associate search terms with images and videos. Editors can then search for and use your media in their own content.

To integrate Amazon Rekognition:

1. Click menu> Admin > Sites & Settings > Sites > Global. The Edit Global widget appears.
2. (Optional) In Integration > AWS Rekognition >Region, enter your AWS region. (If you leave this field blank, Brightspot reads the region from a configuration file.)
   

   

3. Expand Integrations > Image Recognition.
4. From the Provider list, select Amazon Rekognition Recognition Provider. 
5. Under Confidence Levels, do the following:
   
   1. Click add_circle_outline. An Amazon Rekognition Confidence Level form appears.
   2. From the Category list, select one of the available categories.
   3. In the Level field, enter a confidence value for image recognition. Generally, higher confidence levels provide more accurate results (fewer false positives) but may miss some matches (more false negatives).
   4. Repeat steps a–c to configure levels for other categories.
      

      

6. Expand AWS Rekognition (Video), and make the following settings:
   
   1. Toggle on Enable Rekognition Video Service.
   2. In the Region field, enter your AWS region. (If you leave this field blank, Brightspot reads the region from a configuration file.)
   3. In the Time Frame Interval (Seconds) field, enter the number of seconds by which Brightspot groups Rekognition’s results. If you leave this field blank, Brightspot groups the results in 60-second intervals.
   4. Configure the confidence values for video recognition. Generally, higher confidence levels provide more accurate results (fewer false positives) but may miss some matches (more false negatives).
   5. Configure the other fields corresponding to your account settings with AWS.

   

7. Click Save.

Rekognition is configured, and editors can view the results of a Rekognition analysis in the content edit form.

You can use Amazon’s Rekognition service for associating relevant search terms to images or videos you upload to Brightspot.

To submit an image or video to Amazon Rekognition:

1. Create a new image or video.
2. Toward the right of the content edit form, select more_horiz> Metadata, and review the analysis returned from Rekognition.

When editors search for keywords in the search panel related to the image, Brightspot includes the submitted image or video in the search results. Referring to the previous example, if an editor searches for Cat Manx in the search panel, Brightspot includes the above image in the search results.

If your connection to Amazon Video Rekognition is configured to group results by time frame, Brightspot groups the video recognition results accordingly.

Video recognition results grouped by time frame

Referring to the previous illustration, within the interval 45 seconds to 1 minute, Rekognition detected a ball, water, a heart, and a play area in the video.