Merging / Combining separately trained LBPH models
If I have trained a LBPHFaceRecognizer for different faces and stored the result in separate xml files, is ist possible for LBPHFaceRecognizer to read the separate model files and combine them for prediction? When I look into the LBPHFaceRecognizer xml files, I see that the persons (labels) are stored separate anyway. So it should be possible to write a program that can combine these files into one. But it would be nicer if the LBPHFaceRecognizer could do it.
indeed. see src code
that's unlikely to happen, given the current interfaces (and it won't be possible for fisher/eigenfaces)
however, if you do decide to write something like this, please consider contributing it to the community!
Sure I would like to write a module for combining multiple xml models, but in python a LBPHFaceRecognizer cannot read from a string or from a file handle. So the LBPHFaceRecognizer only can read from a real file (or maybe from a pipe). Also there is no function setHistograms(). So the only way to implement this is to read multiple model files, merge them and write them out to a file. This is clumsy and not what I need.