I'm using LocalLBPHistogram.Extractor<CLMDetectedFace> which works well for face recognition but when I change the lighting of the area, the recogniser is unable to recognise anymore. Hopefully I explained this well, What can I use to combat lighting?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Potentially normalisation (FImage#normalise()) or histogram equalisation (HistogramEqualisationProcessor?) might help. You could also add more training examples under different lighting conditions.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Anonymous
Anonymous
-
2014-12-03
Thank you, will try it out.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I'm using LocalLBPHistogram.Extractor<CLMDetectedFace> which works well for face recognition but when I change the lighting of the area, the recogniser is unable to recognise anymore. Hopefully I explained this well, What can I use to combat lighting?
Potentially normalisation (FImage#normalise()) or histogram equalisation (HistogramEqualisationProcessor?) might help. You could also add more training examples under different lighting conditions.
Thank you, will try it out.