Abstract: We present here a system for invariant and robust recognition of
objects from camera images. The system aspires both to be a model for
biological object vision (at least an ontogenetically early form of it) and
to be at the cutting edge of technological achievement. Our model is based
on the principles of temporal feature binding and dynamic link matching.
Objects are stored in the form of two-dimensional aspects. These are
competitively matched against current images. During the matching process,
complete matrices of dynamic links between the image and all models are
refined by a process of rapid self-organization, the final state connecting
only corresponding points in image and object models. As data format for
representing images we use local sets (``jets'') of Gabor-based wavelets.
We have tested the performance of our system by having it recognize human
faces against data bases of more than one hundred images. The system is
invariant with respect to retinal position, and it is robust with respect
to head rotation, scale, facial deformation and illumination.
The source
code for this model is available by anonymous ftp and respective
simulation instructions are given in this report.
Keywords: neural networks, dynamic link matching, face recognition, translation invariance, window of attention