||Face identification
Face identification2020-03-24T12:01:45+00:00

Face Identification on mW power budget using GAP8

Face Identification has attracted a lot of press relating to uses in security applications. It is, however, an interesting feature in many applications. Identifying the owner of a device versus another person can have many uses in creating user experiences. What if one could add face detection to a product at an extra cost of a few euros and at a power consumption compatible with many years of operation on a battery. The GAP8, IoT Application Processor makes this possible!

The input image is taken at Quarter VGA (QVGA) resolution (320 x 240 pixels). The Face Detection algorithm consumes around 1 mW per frame per second and frame rate of 10 frames per second consumes 1/7th fraction of GAP8’s compute power.

In its best power performance Face Reidentification CNN consumes 22mW per frame per second. This is only run when a face is detected and takes approximately 400mSec to evaluate. The CNN evaluated on the Labelled Faces in the Wild dataset (LFW) reaches 96% accuracy.

At these power levels, face identification can be integrated into a wide range of different devices with a very small effect on their battery life.

GreenWaves has released the full face identification stack including the training scripts and the GAP AutoTiler model under Apache 2.0 license.

Contact us

GAPPoc-A , Computer Vision Concept Board

GAPPoc-A is a Proof of Concept Board that can be used for demonstration of battery-operated, edge computer vision applications based on GAP8. The GAPPoc-A board enables battery operated applications developed around algorithms such as face-identification and many others to be quickly assembled and evaluated in the field.

Available in our store

Features:

  • GAP8 ultra-low power IoT Application Processor
  • 64Kbit RAM + 512Kbit Flash  (HyperBus interface)
  • A monochrome image sensor (ON Semiconductor MT9V034) with up to WVGA (752×480) resolution, global shutter, support for 1/2 and 1/4 horizontal/vertical binning, arbitrary size cropping and HDR
  • S-mount holder for interchangeable M12 lens
  • Bluetooth Low Energy module (uBlox NINA B1), controllable through AT commands
  • Battery holder onboard (2/3A primary battery, 3.3V-3.6V)
  • Ultra-low profile “clip-on” connector for optional customer’s satellite board with serial interfaces (SPI/I2C/UART/GPIO)
  • 54mm pitch connectors for feature expansions and for debug
  • Requires an external probe for programming/debug (onboard 10-pin compact JTAG connector)