Face Detection & recognition on microcontroller – AI in electronics and nanotechnology – part I

There are two development trends in the world: creation of centers compressing servers with powerful computing power and the opposite direction – miniaturization in electronics and nanotechnology. Both directions are focused around AI solutions.

Below You can see microcontrollers size comparison to polish coins. Each of the presented models has the same technical parameters and calculation possibilities – differs is only in size

Soon will be released by one of the largest giants of world market, specializing in microcontrollers – the new microcontroller dedicated to AI and Machine Learning. The Portenta H7 will be ready at the end of March 2020. Gives possibilittis Programming it with high-level languages and AI while performing low-latency operations on its customizable hardware. Portenta H7 simultaneously runs high level code along with real time tasks. The design includes two processors that can run tasks in parallel. For example, is possible to execute Arduino compiled code along with MicroPython one, and have both cores to communicate with one another. The Portenta functionality is two-fold, it can either be running like any other embedded microcontroller board, or as the main processor of an embedded computer. Portenta can easily run processes created with TensorFlow™ Lite, gives have one of the cores computing a computer vision algorithm on the fly, while the other could be making low level operationis like controlling a motor, or acting as a user interface. Portenta is usefull when performance is key

Many companies are starting to specialize in nanotechnology and creating smaller and smaller solutions – solutions are amazing.

Today I’d like present microcontroller dedicated to Face Detection & Recognition. Presented microcontroller is a board with a WiFi module module based on the ESP32 system and an OV2640 camera. The camera has a resolution of 2 MPx. The module is characterized by small dimensions and low current in sleep mode. It can be widely used in various IoT applications. It is suitable for intelligent home devices, industrial wireless control, wireless monitoring, wireless QR identification and other IoT applications. Operating temperature: from -20 ° C to 85 ° C. It is great as a camera to monitor the area with wireless access from anywhere in the world. It is possible to connect an external antenna to the microcontroller. Microcontroller ESP32 is the successor to ESP2866.

Schema microcontroller ESP32:

ESP32  function block diagram:

Below on the left side You can see camcorder, and main microcontroller on the right side.

In compare to our microcontrolers:

On the microcontroller you can place your own http or websocket server. Additionally, you can issue a dedicated port for streaming that will work in parallel with other protocols.

ESP-WHO is a face detection and recognition platform that is currently based on Espressif Systems’ ESP32 chip.

ESP-WHO supports development of face detection and recognition applications based around Espressif Systems’ ESP32 chip in the most convenient way. With ESP-WHO, you can easily build up face detection- and recognition-featured applications, for instance:

  • A coffee machine that brews coffee according to your taste preference;
  • Home applicance that will shut off the electricity automatically when unsupervised children are operating them;
  • And other more applications that suit your needs.

In general, the ESP-WHO features will be supported as shown below:

Below You see sample from my tests regarding face detection and recognition. All solution is wrote in pure C language. You can freely modify and write codes – you are only limited by yourself and your imagination.

Soon I will present tests on Youtube channel

and prototype of solution during tests:

Sources:

https://github.com/espressif/esp-who

February 26th, 2020