Face-Detection-on-Microcontrollers VS esp-who

Yes, it's on device (see https://github.com/espressif/esp-who/)

Thanks, I needed some affirmation! The ESP32-EYE I believe still has IPEX connector as seen here or am I missing something?

I guess, but it’s also pretty open code these days now that the S3’s LX7 has some nice vector extensions and other additions for ML applications :)

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

It’s not out of reach for hobbyists, I think, though getting it to run very well might be. And I would certainly tell anyone interested to start with something more powerful first!

This is the unit I use for prototyping, then I figure out what parts I actually need and select the final hardware I want to use for the "production" unit. https://github.com/espressif/esp-who/blob/master/docs/en/get-started/ESP32-S3-EYE_Getting_Started_Guide.md

You can even find smaller (and cheaper and less powerful) devices than RPi which are able to do that – e.g. https://github.com/espressif/esp-who for ESP32-CAM (~$10). Usage of that library is also very straightforward, there are many examples on the internet.

I am using ESP-EYE, i have installed ESP-WHO on system as per instruction, i tried as is example project of ESP WHO to capture image.

The getting started guide and all of its references (links).

Run the following commands in your terminal to download ESP-WHO: git clone --recursive https://github.com/espressif/esp-who.git Remember to use git submodule update --recursive --init to pull and update submodules of ESP-WHO.

From the GitHub specs it looks like there is an integrated charging circuit for the battery soldering points utilizing the usb input as the power supply. I would assume some modicum of protection with a charging circuit but if you’re looking for the best alternative to a battery then I’d wait for smarter people to answer.