nextcloud / nextcloud/recognize

Add a way for user to judge: "This is not a person"

Open
#1,124 5 comments 8 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
PHP
Stars
699
Forks
68
Avg merge
1d 4h
Merged PRs (30d)
5

Description

Describe the feature you'd like to request

I have a lot of faces in the unclustered (NULL) area. Sometimes, some of them get readded to existing clusters, or new shit-clusters are created with them. Often, these are just random faces of passersby in the background or even none-faces.

Here are some examples.
image
image

It's totally acceptable for me that the face recognition is not perfect, but I would like to be able to fix the errors manually. And once fixed they should stay fixed.

Describe the solution you'd like

I would like to remove misdetections completely, so I don't have to worry about them being re-clustered.

Describe alternatives you've considered

Adding all NULL faces to an "Unknown" (shit-)cluster. However, this could cause a problem that newly detected faces might get added to this cluster, too.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no source files, tests, or entry points. Start by locating the flows for unclustered faces, face clustering, and reprocessing, then determine where a user decision can be stored; done means marked misdetections are removed and are not clustered again while newly detected faces remain unaffected.

Written by the indexing model from the issue text.

Assessment

Tech stack
php
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.