This project develops a framework
called Cresceptron for automatic learning for
recognition and segmentation of real-world objects from
their images based on exemplars of performance of such tasks.
The Cresceptron has been tested on the task of visual recognition: recognizing
3-D general objects from 2-D electro-optical images of natural scenes
and segmenting the recognized objects from their cluttered image background.
Specifically, it recognizes and segments image patterns that are
similar to those learned, using a stochastic distortion model and
view-based interpolation, allowing other view points that are moderately
different from those used in learning.
It incorporates both individual learning and class learning; with the
former, each training example is treated as a different individual and with
the later, each example is a sample of a class.
Several types of network structures have been developed, and their properties
are addressed in terms of knowledge recallability, positional invariance,
generalization power, discrimination power and space complexity.
Experiments with a variety of real-world images
are reported to demonstrate the feasibility of the Cresceptron.
J. Weng, N. Ahuja and T. S. Huang, ``Learning recognition and
segmentation of 3-D objects from 2-D images,''
in Proc. 4th International Conf. Computer Vision,
Berlin, Germany, pp. 121-128, May, 1993.
J. Weng, N. Ahuja and T. S. Huang, ``Learning recognition and
segmentation Using the Cresceptron,''
to appear in Int'l Jounral of Computer Vision.
To Weng's Home Page: http://web.cps.msu.edu/~weng/