EVOLUTIONARY MULTI-OBJECTIVE OPTIMISATION OF NEURAL NETWORKS FOR FACE DETECTION
2004 ◽
Vol 04
(03)
◽
pp. 237-253
◽
Keyword(s):
For face recognition from video streams speed and accuracy are vital aspects. The first decision whether a preprocessed image region represents a human face or not is often made by a feed-forward neural network (NN), e.g. in the Viisage-FaceFINDER® video surveillance system. We describe the optimisation of such a NN by a hybrid algorithm combining evolutionary multi-objective optimisation (EMO) and gradient-based learning. The evolved solutions perform considerably faster than an expert-designed architecture without loss of accuracy. We compare an EMO and a single objective approach, both with online search strategy adaptation. It turns out that EMO is preferable to the single objective approach in several respects.
Keyword(s):
Keyword(s):
2021 ◽
Vol 6
(1)
◽
pp. 1-8
Keyword(s):
2019 ◽
Vol 118
◽
pp. 506-521
◽
Keyword(s):
2015 ◽
Vol 1
(1)
◽
pp. 130
◽