For humans, a picture is worth a thousand words, but to a machine, it is just a seemingly random
array of numbers. Although machines are very fast and efficient, they are vastly inferior to
humans for everyday information processing. Algorithms that mimic the way the human brain
computes and learns may be the solution. In this paper we present a theoretical model based
on the observation that images of similar visual perceptions reside in a complex manifold in an
image space. The perceived features are often highly structured and hidden in a complex set
of relationships or high-dimensional abstractions. To model the pattern manifold, we present
a novel learning algorithm using a recurrent neural network. The brain memorizes information
using a dynamical system made of interconnected neurons. Retrieval of information is accomplished
in an associative sense. It starts from an arbitrary state that might be an encoded
representation of a visual image and converges to another state that is stable. The stable state
is what the brain remembers. In designing a recurrent neural network, it is usually of prime
importance to guarantee the convergence in the dynamics of the network. We propose to modify
this picture: if the brain remembers by converging to the state representing familiar patterns, it
should also diverge from such states when presented with an unknown encoded representation
of a visual image belonging to a different category. That is, the identification of an instability
mode is an indication that a presented pattern is far away from any stored pattern and therefore
cannot be associated with current memories. These properties can be used to circumvent the
plasticity-stability dilemma by using the fluctuating mode as an indicator to create new states.
We capture this behavior using a novel neural architecture and learning algorithm, in which
the system performs self-organization utilizing a stability mode and an instability mode for the
dynamical system. Based on this observation we developed a self- organizing line attractor,
which is capable of generating new lines in the feature space to learn unrecognized patterns.
Experiments performed on UMIST pose database and CMU face expression variant database
for face recognition have shown that the proposed nonlinear line attractor is able to successfully
identify the individuals and it provided better recognition rate when compared to the state of
the art face recognition techniques. Experiments on FRGC version 2 database has also provided excellent recognition rate in images captured in complex lighting environments. Experiments
performed on the Japanese female face expression database and Essex Grimace database using
the self organizing line attractor have also shown successful expression invariant face recognition.
These results show that the proposed model is able to create nonlinear manifolds in a
multidimensional feature space to distinguish complex patterns.
|