Face recognition system through body detection. The pipeline first detects human bodies in video streams, then performs face recognition within those regions of interest. This approach improves accuracy in crowded or dynamic environments by reducing false positives and focusing recognition on detected persons.
Updated 2025-09-27 22:19:39 +00:00
Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API
cpp
fbank
features-extraction
kaldi
mfcc
online-feature-extractor
plp
python
pytorch
streaming-feature-extractor
Updated 2025-08-07 13:09:15 +00:00