Back in Nov 2018 (sadly, over two years ago) I posted Plex’ use of imagga (which @pakerwe shows that it now has a facial API). At the time, I posted other facial recognition API options such as Betaface API and LambdaLabs API for Plex to explore.
I have been following ever since… unfortunately for my needs, without facial recognition Plex is nothing but a useless picture repository and browser.
Nail in the coffin was user @Volts finding Elan (CTO & co-founder of Plex) stating that he has no plans for facial recognition.
A pro for some and a con for others is that it is a stand-alone device. It requires its own storage via USB or SSD. This storage can be mapped and accessed from any computer as a network drive.
I have no affiliation to this product, other than to share it with others interested in local facial recognition and jilted by Plex’ lack of consideration for their user community.
14 days to go on their campaign as of Dec 4th.
I am very interested in your opinion of this alternative to Plex.
Good day. I am a new Plex user and just signed up for a lifetime pass. A friend of mine told me it was awesome for music and videos. He’s right - it’s a pretty amazing product. I was an early cloud adopter and loved GPM. When Google messed up that service - I decided to take matters into my own hands and setup a Plex Server in the cloud at Azure. Piece of cake - right. I’m still in the cloud - can stream wherever I am, I control the server, backups are a cinch, and life is good.
Then I started to think about my almost 20 years of photos & videos - what if Google decided to shutdown their Photos product or convert it to something that’s terrible? With the sad state of affairs today politically with groups attacking big tech - what if?
So I decided to look at Plex for personal photos & videos. The feature is there and there is some good, but it leaves a lot to be desired when it comes to tagging, search, albums, and where the heck is facial recognition? I am really disappointed Plex doesn’t have facial recognition built in already. I am curious why Plex as a software company is falling behind the eight ball when there are dozens of known tried and true apis that can accomplish this for us.
Anyway, it would be a no-brainer to switch from Google Photos if this was a thing. I sure hope Plex reconsiders that decision and @elan - get’s this feature on the roadmap and creates a way for us to have acceptable tools to detach from big tech and take control of our own media.
I do not understand why facial recognition is not a part of PLEX. Can anyone explain that to me? PLEX does everything else so well! It seems like its the last piece to the puzzle.
Monument 2 looks cool. I just don’t want to have to deal with hardware at my house. I like the idea of server software that is my own and highly available.
I have been looking for several months for a photo management software that is similar to the experience that Plex has for movies and TV, or Calibre has for eBooks. I recently upgraded to a Plex Pass and love that I now have the capability to get the photos tagged automatically based on subject, but this is more of a nice to have. What is really critical to being able to use Plex for my main photo library is the facial recognition. Really hope that this can be made available to Plex Pass users!
Since Google Photos will end its free unlimited storage on June 1st, 2021. Face recognition/ tagging for Plex will definitely fill this void when that day comes.
Wow I just tried Google Photos to see what all the fuss is about. Not impressed. Really. I actually think more of the plex implementation than before.
There is a fundamental difference in the Google approach however, more than just AI scoring accuracy. They supply some key interactivity which allows you to shape the tagging process. The plex auto tagging model, on the other hand, is zero user interaction. You get whatever the tagger gives you.
Implementing the interaction and tuning functionality, which I think is key, is a big jump. It will involve significant product engineering and the feature would require a lot of time to mature. Not to mention the cost of the machine time required to produce good similarity scores (it’s not for nothing that they limit processing to X images per time period, it’s a processing cost issue)
Bottom line, I’m not holding my breath on this one, and I wouldn’t really blame plex inc for taking a long time to produce it, if ever. I feel like if I really want this in any predictable timeframe I’ll have to implement it myself.
Yeah this definitely a feature I need. I’m migrating away from Google Photos and I will miss the opportunity to say “show me photos of Bob and Jane in 2010”. Surprising how many uses for this kind of query you have when you know it’s available!
I’ll happily continue to support Plex and wait patiently, hopefully it’s somewhere near the top of the list.
Plex should use the data exported from google. There are JSON data like this:
“people”: [{
“name”: “V�a”,
“email”: “”,
“googleProfilePage”: “”,
“x”: 0.11328125,
“y”: 0.0,
“width”: 0.0625,
“height”: 0.1820449
}],
Someone could even create plugin for that.
You can use the opensource library or facerecognition.
