OMRON has unveiled a face recognition module which the firm claims has a maximum recognition speed of 10 times that of a previous model, making it possible to detect a human body four times per second, keeping track of a person within a detection area.
The HVC-P2 B5T module carries out 10 image sensing functions: detection of a human face, hand or body, face recognition, gender detection, age estimation, mood estimation, facial pose estimation, gaze estimation and blink estimation.
The firm says that the module can be used to add face recognition functionality to a system without the need to understand the algorithms or the optical design.
Two types with different camera heads are available. A long range type has an angle of view of 40° x 50° and a wide angle type with 70° x 90°. The module is now also available with a choice of a UART or USB interface.
The module can be used to measure people’s attention to advertisements including digital signage. For instance, the long-distance type of the HVC-P2 can detect people’s gender and age, their sight line and facial expression from a maximum distance of 3 meters, which can help measure the degree of attention of people walking through a railway station pay to a digital signage system installed there.
Another example application of the module is optimization and development of products for sale from vending machines. A wide-angle type module is capable of covering an area 100 cm by 75 cm from a distance of 50 cm, keeping track of people buying naturally from a vending machine, The collected data can be used later for optimum product refill, new product development and marketing activities.
Furthermore, by embedding the module in a variety of equipment and machines, the modules can safeguard people in manufacturing workplaces, keep track of congestion in elevators, and watch out for people under care at nursing homes. The firm notes this can also contribute to the realization of an IoT society.
For more details, view the full Press release.