People: Facial Recognition about photoprism

[lastzero]

No worries! We understand everyone is waiting for this... already moved this issue to the development column on our roadmap... might take a couple of weeks until it can be released. We have a zero bug policy, so those (and major UX issues) get fixed first before we continue working on feature requests. Should be in the interest of all users.

[issuehunt-oss]

@spoorun has funded $100.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $100.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[MrPeteH]

I encourage looking at Picasa3 NOT to use it but to understand what is/was awesome about the UX. A short list:

• Per-face data tagged in the file itself
• Parameters include folders to scan/rescan/ignore for this operation, some kind of quality filter
• Basic operations include: Add name to face (new or existing), combine faces, ignore faces, manually add face rectangles on a photo,
• Basic view modes include: group faces (ie show Joe(56) rather than 56 separate photos of Joe), individual, show whole photo (normally I just want to see thumbnails of recognized faces!), show ignored vs normal
• (Advanced feature: generate slide show with faces resized and recentered on eyes.)

Picasa3 FAILS:

• Database crash loses all ignored pix, often rebuilds face rectangles incorrectly and duplicated (perhaps the metadata is not stored correctly in photos?)

[guysoft]

@lastzero
I would suggest you watch this 1 min video of what #foosel says about github issues during this time. People are edgy and in many cases it just happens to be directed at you. I've been seeing it on several issue trackers the past month.
You are doing a wonderful job managing photoprism. This indeed a sort after feature, and it seems the donations are even building up and its indeed on the development roadmap.

[esimov]

@lastzero thank you, I'm really grateful for your generosity and also for your kind words. 🙏 Also keep in mind that Pigo is still in active development and there is still one big thing left behind in the upcoming future: object recognition and description.

[guysoft]

@lastzero I've been doing computer-visiom detection the past few months at work. If I get today a poof of concept function in go, would you consider an initial UI and backend?

[crsawyer314]

I'm brand new to the project, but I'd like to tackle this issue. If anyone else is working on it already, please lmk, but otherwise could I get it assigned to me?

[lastzero]

Decided to become @esimov's first GitHub Sponsor 🥳 🎈

He's maintaining Pigo and a bunch of other libraries that look amazing. Can't wait to give them a try!

[dror3go]

Is there a plan to support pets recognition, or is it out of the scope of this issue?

[jimmcslim]

I'm wondering if this could be implemented with some sort of provider pattern? Ship a default local implementation, but also provide scope for an implementation that relies upon a cloud-based facial recognition provider, such as the Computer Vision APIs that are part of Azure Cognitive Services? I appreciate this might not be in the spirit of the 'own your data' ethos of PhotoPrism, but just putting it out there as a suggestion.

[JAKAMI99]

fund! to the moon

[MrPeteH]

@nicrf I agree with you, and @lastzero ... ABSOLUTELY you don't want to limit face recognition to "users."
Remember: faces likely include people who are not even alive anymore... or may be babies :)

I don't know too many one year old coders

[alexislefebvre]

Have you considered using a separate Docker image for image detection? Maybe it already exists and it can be plugged through an HTTP API, it would avoid managing the dependencies.

[Gestas]

I've been testing the approach above vs requiring users to create a per-person. This is with go-face directly, no PhotoPrism integration at this point. I'm using my personal photos, ~18K images. Some with faces, others without. I'm getting a significantly better user experience with the latter approach. I'm not an expert in this space, perhaps I'm doing something wrong.

When I use go-face to automatically create models I end up with collections of faces 100's big. For adults the rate of incorrect matches can be as high as 20%, for children 45%. The user experience required to correct the model is poor, I have to remove images. If instead I label 20-30 images first the run the classifier I get better results with a significantly better user experience.

I suggest we prompt users to label a set of photos first then run the classifier. For images with unknown faces we could add an "unlabeled-face" tag that would allow users to easily find and tag more faces.

[guysoft]

I would vote against that because you want it ti be self-hosted. And it can be.
I seem to think at this point we could

1. Implement something from scratch
2. Wait till something comes out in go
3. Port what ownphoto used and have a way to interface to it with go

[pluja]

@lastzero I'm very sorry if it seemed like I was rushing you into this. I didn't mean it that way at all. I was just asking out of curiosity. It is clear that merging PRs is very important!

[lostmaniac]

How long can I expect to use this feature? Looking forward to face recognition

[issuehunt-oss]

An anonymous user has funded $5.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@urbiops has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[lastzero]

@guysoft Any help with this much appreciated! We should tag a stable release first. Batch edit & facial recognition is on the top of our todo list for the time after.

[issuehunt-oss]

@cloudfreeshop has funded $25.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@friesoft has funded $10.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[lastzero]

More than happy to start with this. However, these folks are waiting for their PRs to be reviewed and merged: https://github.com/photoprism/photoprism/pulls

Tell me what to do... ignore them?

[lastzero]

Interesting! So many options... was different when we started... patience pays out :)

https://github.com/esimov/pigo received major improvements as well... I like the simplicity and that it doesn't have external dependencies (as we already have enough to maintain).

[lastzero]

@cgudea You're most welcome to support our work via GitHub Sponsors:

https://github.com/sponsors/lastzero

No contributions there yet as GitHub Sponsors is pretty new. They will match any donation in the first year!

Don't expect to see a pull request for facial recognition anytime soon, it's too complex. We'll start working on it once albums and sharing are done. Financial support makes a major difference as we otherwise have to stop development frequently to do commercial projects.

@lastzero If you want to get rid of the dependency of dlib, you can try the way that ownphotos does facial clustering. https://github.com/hooram/ownphotos/blob/dev/api/face_clustering.py

You can use any tensorflow CNN model that extracts facial features, and do a kmeans on them with https://github.com/muesli/kmeans

[lastzero]

@totti4ever We're currently not modifying ANY originals to protect them. But we can certainly provide metadata incl faces and labels as sidecar file, database dump or via API.

[issuehunt-oss]

@totempaaltj has funded $30.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@uluvil3gcs has funded $22.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@luxumbra27 has funded $10.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $10.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[guysoft]

I would advise against that since I think Photoprism stands for self hosting. The Readme says "Say goodbye to solutions that force you to upload your visual memories to the cloud". And using Picasa would be exactly the opposite of that.
Moreover it should be possible to have a facial recognition core that is self-hosted like there is in ownphotos (which has been abandoned).

[lastzero]

@crsawyer314 Thank you! We know facial recognition is pretty popular (and also want it for ourselves), but need to get a stable release and geodata api out of the door first. As there are various ways to solve this (and many contributors who might be able to help) it should be a coordinated effort.

In a nutshell:

• We certainly don't want to use external services or scripting languages
• Second best option is using a popular library like OpenCV
• The ideal solution is Go-based and doesn't require any external dependencies

What about we're starting with this in January? Of course, prototypes and links to libraries may be posted at any time.

[issuehunt-oss]

An anonymous user has funded $25.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[lastzero]

@el-tiuri For this, we need a proper XML / XMP parser first. The one that comes with Go is "not so good" and currently being rewritten from what I know. Once all this work is done, it may be easy to import faces from XMP.

[thomaseizinger]

How long can I expect to use this feature? Looking forward to face recognition

It is gonna be faster if you join the list of sponsors :)

[dtaivpp]

Going to look into starting this. Also, I think there should be a UI. Don't get me wrong I think that grouping people under a random tag would be less useful than allowing users to name their people.

Here are my thoughts for the logic and you all can let me know what you think. I haven' t looked too much over the code base but will do that before implementing this so it is integrated with native triggers.

Backend:

Application Starts
    if no models exist:
        start scanning all files and generating models
        models are randomly named and tags are added
    else:
        on new photo entry
        check against current models
        if no matching models
            create new random tag
        else
            update with random tag / or name if exists

Frontend:

Show Sample image with peoples faces and tag
    allow the user to change the tag to name
    on name entry, update model to use name to tag

I just wanted to put some sample logic out there so we can break this down into a few steps and get it progressively added. I think the first phase would be getting Go-Face creating models and grouping faces by random tag.

[dtaivpp]

Small update, it seems we will only need to tag the photos. I just noticed there is already support for re-naming tags. I'll start looking into just classifying and randomly naming them. Then users can simply update the labels. The tricky part will be photos with more than one person but we can cross that bridge when we get there.

[Gestas]

@dtaivpp I think @lastzero is right, we need to be able to differentiate between labels (nouns) and faces during a search. E.g in English "Forest" can be a set of trees or a name for a human. A user might want to search for "Forest" the person and not a set of trees.

[Gestas]

@lastzero I think it would make sense to extend the , model to all parameters. E,g - &camera=2,3, &year=2018,2019. Should I open a separate feature request for this?

@dtaivpp that's doable. I think it's not something we need to include in the MVP release, do you?

[totti4ever]

I totally understand that you don't want to edit files being a front-end software. Although I miss software to properly process my images and add information about recognized people in the pictures.

So if you do that anyway, I'd just love to also write them to the files - whether through the UI or by some CLI or API call, I wouldn't mind

[mubashir-rehman]

@guysoft Picasa3D is also deprecated and works offline and there is no working option to upload files to cloud(even if available I never used it).
Sorry for cluttering this issue.

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[lastzero]

@nicrf Going to look into this in more detail later this month. In principle, our users table is for actual users (or placeholders like anonymous and guest) while we plan to use faces and/or people tables for facial recognition and tagging.

[IssueHuntBot]

@issuehuntfest has funded $40.00 to this issue. See it on IssueHunt

[lastzero]

@trosel We already have object detection / classification, without position however. Facial recognition is different from classification in that you need parameters for face parts as output to do the actual recognition based on a clusters (and not just detection).

What specific library do you refer to?

[cgudea]

@lastzero totally understandable. I'm a huge fan of the goals of this project and will be looking to contribute after the holidays in January either financially or via development (I am a mobile developer at my dayjob).

[lastzero]

We could split the search string after ,

[issuehunt-oss]

An anonymous user has funded $10.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[elboletaire]

Dude this rises like bitcoin in early 2016. @guysoft have you started working on it? I've been subscribed to this issue for a while, and now looks like it's worth taking some time for it 😂

I'm really busy right now but, if no one starts doing this, I may try to do it during the next weeks.

Ofc after knowing no one is currently working on it. And I don't want to add any pressure. If someone is working on it, please, update us! :)

[guysoft]

I was searching for face clustering tools for go and got stuck.
there is detection and recognition, but no clustering

[ChrisFab16]

I would vote against that because you want it ti be self-hosted. And it can be.
I seem to think at this point we could

1. Implement something from scratch

2. Wait till something comes out in go

3. Port what ownphoto used and have a way to interface to it with go

As far as I can tell, there has been activity on the ownphoto fork in this space as well, so it's likely worth taking a look at the current state.

[guysoft]

FYI pigo only detects location of faces, it can't compute distance between them (as in so you can cluster them and then understand they are the same persion). See esimov/pigo#38

[lastzero]

Would be great to know the roadmap of related Go machine learning projects / libraries. I know recognition was not possible when I checked last time, just detection. Maybe there is something in the pipeline it's worth waiting for?

[issuehunt-oss]

@cloudfreeshop has funded $25.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $15.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $2.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@kreusen has funded $10.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@setime has funded $4.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@conrad82 has funded $5.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[husayt]

Here are some more libraries to consider:

• Openface

• https://github.com/ageitgey/face_recognition

The latter is using Dlib state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark

[lastzero]

I'd prefer a library implemented in Go to improve performance and reduce complexity.

[devzsolt]

As a proof of concept you can create a small interface to an external tool (eg. https://github.com/ageitgey/face_recognition using its CLI) and then later it's possible to replace it with a native Go lib. I think it would speed up the early development, this Python lib looks pretty much mature.

[xeoncross]

The easiest way to do this is simply to slap https://github.com/esimov/pigo into the project as a pure Go include.

[lastzero]

@xeoncross Thanks! But Pigo is just face detection, not face recognition...

See https://github.com/photoprism/photoprism/wiki/Face-Recognition

[lastzero]

This looks good to me on first sight: https://github.com/jdeng/goface

[trosel]

Could object detection be included in this request as well? Some libraries work with both faces and objects I think.

[cgudea]

I don't have any go experience but I'd really like to see this feature implemented. Is there anyone currently doing work on this? If so, would adding money onto the bounty help expedite the development?

[lastzero]

@cgudea Thank you <3

[lastzero]

@ulinuxp Thank you! Hopefully we'll soon have time to start with this...

[guysoft]

Here are some more libraries to consider:

* [Openface](https://cmusatyalab.github.io/openface/demo-2-comparison/)

* https://github.com/ageitgey/face_recognition

The latter is using Dlib state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark

The exact same engine is used here in go
https://github.com/Kagami/go-face

[dunderpate]

As a user, the approach of labeling a set of photos makes sense. Do we have a flow for re-labeling images that are incorrectly labeled, or to re-classify once the models are updated in order to correct mislabeled images? Thanks for the work on this, this project is getting really close to a viable Photos alternative once this is added, for my purposes at least.

[lastzero]

Labels are only meant for object classification, not for face recognition. We need to use a separate database table with different columns for this.

[dtaivpp]

@lastzero Can you explain to me why that is the case? I am new to this project and am not sure I understand the whole flow right now. Would adding names as labels interfere with other processes?

@Gestas # Edit, I see you don't have it integrated yet. Disregard this.# do you have a fork I could look at? I'm curious if the model may just need some fine-tuning. For example, we could put a higher threshold on what justifies a match and then as more data is added rerun and collect ones that previously didn't have a high enough confidence.

[guysoft]

You will likely need a "face id" and then that face id would link to information about the person (for example a name). That would require another table.

[Gestas]

Are there any changes to the search API in the works? I'd like to support compound face searches. Given the current design it looks like we would add a "face" parameter to the API but that would only support searching on a single name.

[dtaivpp]

@lastzero that is probably the best option with the least time to develop. I could see the benefit of being able to search for pictures with multiple people's faces @Gestas

Another potential challenge is identifying which face the tag is being related to. Say for example every time I go out with my friend Mike, I also go with Carl. I will only have pictures of both Mike and Carl so on the front end there needs to be a way to distinguish which is which. That way when I do take a picture of just me and Mike it isn't confused.

[totti4ever]

One question: Would the recognized face just be stored in an internal database of photoprism or would you consider an option to also store it as label to the picture itself? This should only happen on specific request of the user to not update thousands of files coincidentally, but on the other hand I don't want a lock-in and be able to access the recognized people by using any other software that reads standard meta tags

[eliliam]

@lastzero Are there any updates on this? With all of these donations coming in, there hasn't been any updates here in over six months. Seriously, if PhotoPrism pulls this off, that would be a huge win for the project. It seems as if all other open source solutions have dropped off the map in terms of facial recognition.

[Extarys]

@elboletaire [Off topic:] the goal is to wait as long as possible and get all the gold at the end. It looks like that though

[mubashir-rehman]

Even though Picasa3D(by Google) is deprecated, it still works very well at recognizing faces with small errors. Also, Digikam is also working on such a feature and it looks promising(not in GO).

[guysoft]

I think it might be worth just using this:
http://openbiometrics.org/

[issuehunt-oss]

An anonymous user has funded $2.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[dtaivpp]

@mogwai the biggest issue is not recognizing but doing clustering to detect similar faces.

[nicrf]

Hi,

Being new to your project,In order to create a manual tag I want to know if you would be more in favor of a complete "entity" for the person "tag" or would you prefer to use "users" as the base person (name, Dob, etc.. )?

Because, I was tinking about that, and you don't want always create a new user for a peaple tag (like all friend you know).

So if I am rigth , I will use two new entity, person and person tag, where the person can be linked "Has One' to user if it is not null.

Something like that :

type Person struct {
	ID            	string    	`gorm:"type:VARBINARY(42);primary_key;auto_increment:false;" json:"PlaceID" yaml:"PlaceID"`
	PersonFullName    	string    	`gorm:"type:VARBINARY(755);unique_index;" json:"FullName" yaml:"FullName"`
	PersonUserId     	*string    	`gorm:"type:VARCHAR(42);" json:"UserId" yaml:"UserId,omitempty"`
	PersonBoD     	*time.Time 	`json:"BoD" yaml:"BoD,omitempty"`
	PersonDeadDate     	*time.Time 	`json:"DeadDate" yaml:"DeadDate,omitempty"`
	PhotoCount    int       `gorm:"default:1" json:"PhotoCount" yaml:"-"`
	PlaceCount    int       `gorm:"default:1" json:"PlaceCount" yaml:"-"`
	CreatedAt     time.Time `json:"CreatedAt" yaml:"-"`
	UpdatedAt     time.Time `json:"UpdatedAt" yaml:"-"`
	DeletedAt     *time.Time  `sql:"index" json:"DeletedAt" yaml:"DeletedAt,omitempty"`
//	PhotoPersonTag []PhotoPersonTag
}


type PersonTag  struct {
	ID            	string    	`gorm:"type:VARBINARY(42);primary_key;auto_increment:false;" json:"PlaceID" yaml:"PlaceID"`
	PersonId     	*string    	`gorm:"type:VARCHAR(42);" json:"PersonId" yaml:"PersonId,omitempty"`
	PhotoUID     	*string    	`gorm:"type:VARCHAR(42);" json:"PhotoUID" yaml:"PhotoUID,omitempty"`
     //MugTag  Information
	PhotoX1    int       `gorm:"default:1" json:"X1" yaml:"X1"`
	PhotoX2    int       `gorm:"default:1" json:"X2" yaml:"X2"`
	PhotoY1    int       `gorm:"default:1" json:"Y1" yaml:"Y1"`
	PhotoY2    int       `gorm:"default:1" json:"Y2" yaml:"Y2"`
	CreatedAt     time.Time `json:"CreatedAt" yaml:"-"`
	UpdatedAt     time.Time `json:"UpdatedAt" yaml:"-"`
	DeletedAt     *time.Time  `sql:"index" json:"DeletedAt" yaml:"DeletedAt,omitempty"`
}

Is this right for you?

[pluja]

Hey, I'm just curious how is this going? I see on the roadmap that this is in the development state 👀

[Iscanniya]

So nice to hear, you're putting it into development! The acceptance criteria doesn't state the possibility to import allready found faces by google. May this be another rfc? Cause Google Photos puts all the names of found people in the people section of their json-File...

[lastzero]

Haven't noticed Google exports this... but also didn't tag people. Can you provide us with an example?

[Iscanniya]

Of course, here's one example of one person tagged.

{
  "title": "foobar.jpg",
  "description": "",
  "imageViews": "0",
  "creationTime": {
    "timestamp": "1549546798",
    "formatted": "07.02.2019, 13:39:58 UTC"
  },
  "modificationTime": {
    "timestamp": "1612034183",
    "formatted": "30.01.2021, 19:16:23 UTC"
  },
  "photoTakenTime": {
    "timestamp": "1148246652",
    "formatted": "21.05.2006, 21:24:12 UTC"
  },
  "geoData": {
    "latitude": 0.0,
    "longitude": 0.0,
    "altitude": 0.0,
    "latitudeSpan": 0.0,
    "longitudeSpan": 0.0
  },
  "geoDataExif": {
    "latitude": 0.0,
    "longitude": 0.0,
    "altitude": 0.0,
    "latitudeSpan": 0.0,
    "longitudeSpan": 0.0
  },
  "people": [{
    "name": "John Doe"
  }],
  "googlePhotosOrigin": {
    "driveDesktopUploader": {
    }
  }
}

[guysoft]

That tells you who, but not where.
Not sure how you plan ti define the feature. Ideally face clustering would help you detect new faces. And to cluster you will need a distance metric.

[el-tiuri]

If importing previously tagged faces is something you'd want to implement (I think it'd be great!) importing from XMP metadata should probably be doable. It defines an area, coordinates and the name associated with the face. I attached an XMP file (renamed to txt so I could upload it here) with a person tagged. To anonymise it I changed the name to "Dummy data".

DSCF1911.JPG.txt

[issuehunt-oss]

@conrad82 has funded $5.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[pluja]

I know you want to use a written-in-go library, but maybe this project I just found might help somehow. So I will leave the link to the repo just in case:
https://github.com/exadel-inc/CompreFace

[issuehunt-oss]

An anonymous user has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.

[issuehunt-oss]

@angelnu has funded $20.00 to this issue.

---

• Submit pull request via IssueHunt to receive this reward.
• Want to contribute? Chip in to this issue via IssueHunt.
• Checkout the IssueHunt Issue Explorer to see more funded issues.
• Need help from developers? Add your repository on IssueHunt to raise funds.