Summary

This chapter has shown you all the steps required to create a real-time face recognition app, with enough preprocessing to allow some differences between the training set conditions and the testing set conditions, just using basic algorithms. We used face detection to find the location of a face within the camera image, followed by several forms of face preprocessing to reduce the effects of different lighting conditions, camera and face orientations, and facial expressions. We then trained an Eigenfaces or Fisherfaces machine-learning system with the preprocessed faces we collected, and finally we performed face recognition to see who the person is with face verification providing a confidence metric in case it is an unknown person.

Rather than providing a command-line tool that processes image files in an offline manner, we combined all the preceding steps into a self-contained real-time GUI program to allow immediate use of the face recognition system. You should be able to modify...