machine intelligence, shape-matching, robotics, evolutionary algorithms
Shape matching techniques are important in machine intelligence, especially in applications such as robotics. Currently, there are three major approaches to shape recognition: statistical, syntactic and neural approaches. This paper presents a fourth approach: evolutionary algorithms. A steady state memetic algorithm is shown to be successful in matching shapes even when they are partially obscured, and even in the presence of noise in the input image.
Ozcan, Ender and Mohan, Chilukuri K., "Steady State Memetic Algorithm for Partial Shape Matching" (1998). Electrical Engineering and Computer Science. Paper 78.