[fprint] Working with small sensors

[Vasily Khoruzhick]

On Fri, Jun 12, 2020 at 8:05 AM Indev <indev12 at gmail.com> wrote:
>
> I've heard that fprint matching doesn't work well with small sensors.
>
> In my case (issue #162), the device returns 114x57 images and there is probably not much minutiae to extract. I am certain that it is a press sensor, even though it returns multiple images during communication. Despite the fact that it's hard to find any specification for the device, Acer Swift 3 promo shows exactly that.
>
> When running enroll and then verify examples, I get "score 0" on every verify.
>
> Basically, my questions are:
>
> Is this a small sensor problem and is there really too little minutiae?
> What is the state of small sensors matching? Are there any working drivers for small sensors?

It's in very early stages. I've opened 2 issues recently: [1] [2]
I'm slowly working on 1st and I don't have any timeframe on when it'll
be ready. Basically I'm working on it in my spare time and it's not
the only hobby project I'm working on right now.

> How much minutiae is enough to work?

I'd say at least 10-15

> In my driver code, how can i check minutiae count before calling fpi_image_device_image_captured, for example, to prevent submitting images with low minutiae count?

It's in generic code, not in driver. Moreover I expect it to be
impossible to extract minutiae for every image that you get off the
sensor - it's quite CPU-intensive process.

> What are other options to make my device work, maybe by using multiple images?

Help with [1] and [2] or do your own research on fingerprint matching
for small area sensors and start a new discussion?

Regards,
Vasily

[1] https://gitlab.freedesktop.org/libfprint/libfprint/-/issues/271
[2] https://gitlab.freedesktop.org/libfprint/libfprint/-/issues/272

>
> _______________________________________________
> fprint mailing list
> fprint at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/fprint