deepinsight / deepinsight/insightface
Image quality to have the best face recognition performance
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Dear,
It might be a noob but I'm wondering which kind of image quality is bad for face feature extractor?
Searching around in Google brought me some concepts about image blur level, contrast, illumination, sharpness,...too many things and I'm not sure which one is bad for face extractor, which one can bring the best performance.
What is your idea about it? Do you have any experiments with image enhancement methods for face recognition? Which one brought the best performance?
Thanks,
Can
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.