Managing Facial Recognition (v2 Beta)

Topics included in this article:

• Camera Positioning and Zooming
  • Best Practices
• Search Faces
  • Navigate to Search Faces
  • Search and Filter
  • Matched Face Event
  • Unmatched Face Event
• Manage Faces
  • Navigate to Manage Faces
  • Photo Selection Best Practices
  • Add a Person
  • Bulk Add People
  • Edit a Person
    • Edit a Name
    • Change Matchmaker Photos
  • Delete a Person
  • Add Labels
  • Matchmaker Images
  • AI Matching Threshold
• Helpful Links
• Contact Support or Sales

Faces v2 is currently in BETA and not all organizations have been migrated over.

Camera Positioning and Zooming

The camera position is one of the first aspects of setting up successful facial recognition. Lighting, angles, and position all play an important part in the system when capturing faces that can be analyzed with facial recognition. 

Best Practices

• Mounting Position: Place the camera as close to face level as possible with an angle under 30° from all directions (up, down, left, right).
• Camera Distance: Mount at a distance that provides approximately 100 PPF (pixels per foot) on the face at the desired capture point. For maximum distance guidelines, refer to the article on Optics and Object Distances for Analytics. Using shorter distances than the maximum listed can help reduce bandwidth consumption. 
• Lighting: Ensure the camera faces inward to avoid back-lighting and is placed in a well-lit area. Minimize shadows and glare on the face.
• Focus: Adjust the camera’s zoom to focus on the intended facial capture area.
• Encourage Attention: Position the camera where people will naturally look toward it, such as near a sign or graphic to draw attention.
• Uncooperative Scenarios: For cases where individuals don’t actively engage with the camera, try to optimize face capture angles for better results (e.g., avoid side or downward views). Anything that can be done to get a straight shot of the face will enhance the feature's results.
• Unique People Counting Feature: For unique people counting, Rhombus recommends mounting the camera above an exit door to capture faces as people leave.

Search Faces

Navigate to Search Faces

1. Click on the "Investigations" tab and select "Faces."

2. Click "Search."

Search and Filter

You can search by a name that has already had a match. 

You can filter the results by a time frame, a location(s), a camera(s), or a label(s). 

Toggle on the "Show only matched faces" to filter out any unmatched faces. 

Matched Face Event

Matched face events will provide the confidence percentage the model was when matching the face and the associated name. 

If the match is incorrect, click the three dots to the right of the name. You will have the option to mark the instance as "Not a face" or "Remove as match." You can also directly edit the name of the match by clicking the edit pencil next to the name. 

Unmatched Face Event

An unmatched face event is an instance where the confidence threshold for matching the face did not meet the minimum set in the "AI Matching Threshold" section and thus could not confidently match to a person saved in the system. 

To edit the event, click on the three dots next to "Unmatched." Here, you can either mark the event as "Not a face" or associate it with a person by adding their name. 

Note: Adding a name to an unmatched face event will not affect future detection accuracy for that person. All face matching is determined only by the matchmakers loaded and selected in the "Manage Faces" section.

If the name does not already exist as a saved person, you can do a quick add to create a new profile. This will take you to the "Add a Person" flow. 

Manage Faces

Navigate to Manage Faces

1. Click on the "Investigations" tab and select "Faces."

2. Click "Manage."

Photo Selection Best Practices

For optimal face matching, Rhombus recommends a few best practices when choosing images to use as matchmakers. 

• Start with "Upload": It is recommended to start with high-quality front views for the uploaded photo and see how the system performs before adding in additional matchmakers from captured footage. Only one uploaded photo per person is needed. 
• Image Clarity: Use clear images or captures with minimal to no blurring.
• Face Angle: For the "Upload" photo, it is recommended to use a high-quality front-facing image of the person. For additional "Captures from Footage" images, selecting a variety of small angles will assist the model. It is not recommended to have full side views (90 degrees) or multiples of the same angle.
• Maintain Updates: If a person has any significant changes, such as growing a beard or getting a haircut, it is recommended to re-upload an image of that person and update any additional matchmakers. 

Add a Person

Bulk Add People

Edit a Person

Edit a Name

1. Click on the pencil icon next to the person's name.

2. Write the new name and click "Save."

Change Matchmaker Photos

Delete a Person

Add Labels

1. Click the label icon under a person's name.

2. Type in the word you wish to use for a label. If it doesn't already exist, click "Create label [name]." If it exists and is actively being used with another person, you can select it from the dropdown list.  Removing a label from all people it is associated with will permanently remove that label from the dropdown list.

Matchmaker Images

These are the faces that will be used for all facial matching for each person. A person can be associated with a maximum of up to five matchmaker photos at a time, with one being an uploaded image and the others being images captured by a Rhombus camera.

Images that can be selected as matchmakers have already gone through a preliminary check. This check looks for a minimum upload quality and meets a specified confidence level. A low confidence level image will not be available to be selected, even if it is a captured image from an event on the search page. 

You can add matchmakers when adding an individual new person or after a profile has been created by selecting the "+" symbol in the "Captures From Footage" section. 

AI Matching Threshold

Here, you can adjust the threshold the AI Facial Recognition model uses to determine a match with a saved person. The default is set to 70%, which represents the minimum confidence level required to name a person automatically. 

Increasing confidence improves accuracy but may filter out detections. Decreasing confidence reduces accuracy, which may result in false positives. Adjusting confidence doesn't account for environmental factors that impact AI performance. Learn more in the AI Confidence Settings article. 

Helpful Links

• Features
• Digital Zoom and Pan
• Optics and Object Distances for Analytics
• How to Use the Investigations Tab
• Face Alerts with Labels
• Creating and assigning camera alert policies
• AI Confidence Settings

Contact Support or Sales

Have more questions? Contact Rhombus Support at +1 (877) 746-6797 option 2 or support@rhombus.com.

Interested in learning more? Contact Rhombus Sales at +1 (877) 746-6797 option 1 or sales@rhombus.com.