Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Are we using the same Google Photos? I've found Immich face recognition and context/object search to be miles better than Google Photos. In particular, Google Photos is exceptionally bad at distinguishing non-European looking faces (though it's not great in general), and it completely gave up on updating / scanning new photos in 2024 after I imported party photos with a lot of different people.

Almost all my Google Photos "people" are mix-and-matched similar looking faces, so it's borderline useless. Immich isn't perfect, but it gives me the control to rerun face recognition and reassign faces when I want, even on my ancient GTX 1060.





The main issues I see are immich identifying things like statues or paintings as people, and not dealing with people (especially kids) aging.

Google photos isn't perfect either but I never saw these kind of issues when I was still using it.


My google photos doesn't even seem to support facial recognition, maybe I turned it off somehow at some point, but it doesn't seem like google photos supports manually selecting a face (a face that isn't detected), which is something I use a ton with Immich, it is very convenient, even if a bit tedious if going through a backlog.

Annoyingly you can't create a person that way yet with immich, but that's where digikam helps.


Immich manages to detect my kids faces much better than expected. I only have two years, but it is spot on with kid #1 from newborn to 2yo, and it manages to not mix up the new baby photos of #2 with the baby photos of #1. In my 44k photos there are zero statues face detected, the only flukes are a few photos from a restaurant with a celebrity picture wall.

Don’t all non-European people look alike?



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: