reply to post by LordBucket
FYI, the Dept of Computer Science, University of Mass has done an unclassified research project funded by DARPA on face recognition. Their sample
group is a tea party crowd (no lie) and they show photos of several faces (permission given?, doubt it) as examples to make the points of their
findings. In the paper summary, they actually use the word "exciting" to sum up their research.
The title is "On Multi-scale differential features for face recognition". I don't know how to cut and paste a PDF, but maybe you do.
From the Intro:
"Face recognition technologies can significantly impact
authentication, monitoring and image indexing applications.
This paper presents an algorithm to compute similarity
of faces as a whole. The task is to query a database
using the image of a face and then have the system either
ascertain its identity, or retrieve the top similar
matches. As such, the technique is general and has hitherto
been used successfully in image retrieval tasks such
as finding similar scenes, trademarks, binary shapes and
textures [23, 24, 25]. The approach is based on the two hypotheses;
first that visual appearance of a face plays an important
role in judging similarity and second, multi-scale
differential features of the image brightness surface form
effective appearance features."