ageitgey / ageitgey/face_recognition
Counting the number of different faces from a list of video
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 56.8k
- Forks
- 13.7k
- PR merge metrics
- No merged PRs in 30d
Description
I'm planning to create a project to use the face recognition to help me to choose the footages from a list of video.
I have a list of footages (over 100 HD video footages from DV camcorder), which I have to play all the video every time to get the best shot for further editing. One of the criteria would be getting as much as faces in the video. I'm just wonder, is it possible to write a batch program to scan all the footages and list out the number of faces appear in each footage?
As far as I know, the face_recognition can locate as much as faces in a frame of the video, but how to count the number of people in the footage by faces, and retrieve the number of different faces appear in the footage?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue does not name any repository files, tests, or entry points. First clarify whether the desired output is faces per frame, people appearing across a full video, or distinct identities; done would require a defined batch workflow and verifiable counts for each footage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100