Facial recognition vs Object recognition, are they different…. Should you care?

A facial recognition system is a technology capable of identifying or verifying a person from a digital image or a video frame from a video source. There are multiple methods in which facial recognition systems work, but in general, they work by comparing selected facial features from given image with faces within a database.

Portrait of a happy woman expressing different emotions

Object detection as it may sound however is more interested in a class of object rather than a specific object such as an individual’s face. By detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos.

Machine Learning object detection and artificial intelligence. Application detect object in picture.

The goal of object detection is to detect all instances of objects from a known class, such as people, cars or faces in an image. This ability lends very well to such things as counting the number of cars in a carpark, people in a shop or even dwell time in an area without imposing on an individual’s privacy.

How object detection works

Lets take an example of a person being detected on a Meraki MV camera, Each detection is reported with some form of pose information. This could be as simple as the location of the object (a person or car), it’s x & y coordinates and scale, that’s it. This allows companies such as Presence Orb to then collate the information to become analytics which are privacy compliant accurate and informative to the decision makers in venues around the globe.

Historically this sort of object detection would have been done using PC with strong GPU or top end CPU driven machines on site, this was cumbersome to install and required server maintenance storage and the costs associated with each of these per store or venue. Thankfully this is no longer the case

Using Meraki MV Sense Cameras with a powerful onboard processor and a unique cutting-edge architecture, Meraki Smart Cameras run object detection, classification, and tracking directly on the edge.

Through the API endpoints of MV Sense, this machine learning/computer vision data becomes available for you to use in your applications, providing high-value data and business insights without the high-cost compute infrastructure that is typical in computer vision and video analytics. MV Sense is designed to allow you to truly integrate the edge-computing capabilities of Meraki MV Smart Cameras into business solutions while keeping in-line with Meraki simplicity.

To learn more about how Presence Orb can work with your Meraki network including MR series access points and MV series cameras please do get in touch.