Retail Signage Uses Face Rec to Determine Shoppers' Age, Gender

Accoring to a Technology Review, CognoVision has developed face recognition software that can determine a person's gender and approximate age for retail use. CognoVision's fully automated Anonymous Impression Metric (AIM) is an audience measurement system that uses face detection and tracking technology to find viewers' faces captured by digital optic devices.

For privacy purposes, the AIM system is designed to ensure that the data detected and aggregated cannot be associated or otherwise linked with any specific individual. No personally identifiable information is ever collected, as the system ensures only anonymous data is aggregated to provide meaningful metrics.

CognoVision's AIM platform can measure actual impressions: the number of people who look at displays; the length of impressions: how long people look for; potential audience size: the number of people who walk by; dwell time: how long people stay near the displays; and anonymous demographics: gender and age bracket.

Machine vision algorithms analyze facial features to generate demographic information, and the software collects information on the size and shape of the face and the distance between features, and compares those data points with information previously categorized in a database. The accuracy ranges from 85 to 95 percent.