vision by evolutionary optimization

[Anoop K. Bhattacharjya]

Reprints are available on request for the following paper:

Bhattacharjya, A. K., and  Roysam, B.,"Joint Solution of Low,
Intermediate and High-Level Vision Tasks by Evolutionary
Optimization: Application to Computer Vision at Low SNR,"
IEEE Trans. Neural Networks, Vol. 5, No. 1, pp. 83-95, 1994.

Please direct reprint requests to roysam at ecse.rpi.edu. An abstract
of the paper is given below:



                           ABSTRACT


 Methods for conducting model-based computer vision from low-
SNR (~ 1dB) image data are presented. Conventional algorithms
break down in this regime due to a cascading of noise artifacts,
and inconsistencies arising from the lack of optimal interaction
between high and low-level processing. These problems are addressed
by solving low-level problems such as intensity estimation,
segmentation, and boundary estimation jointly (synergistically) with
intermediate-level problems such as the estimation of position,
magnification and orientation, and high-level problems such as object
identification and scene interpretation. This is achieved by formulating
a single objective function that incorporates all the data and object
models, and a hierarchy of constraints in a Bayesian framework. All
image processing operations, including those that exploit the low and
high-level variables to satisfy multi-level pattern constraints,
result directly from a parallel multi-trajectory global optimization
algorithm.

 Experiments with simulated low-count (7-9 photons/pixel) 2-D Poisson
images demonstrate that compared to non-joint methods, a joint solution
not only results in more reliable scene interpretation, but also a
superior estimation of low-level image variables. Typically, most object
parameters are estimated to within a 5% accuracy, even with overlap
and partial occlusion.