A medial axis transformation language for recongnizing aircraft silhouettes using a genetic search technique
Jill Laura Giles · Journal of International Crisis and Risk Communication Research · 1991
Aircraft recognition and classification are salient elements of a number of aerospace systems. This work explores aircraft classification using genetic algorithms for search through a classification space. Two main algorithms comprise this approach. The first produces an assortment of shapes derived from a medial axis transform language (MAT), by establishing a set of genes, a chromosome, that portrays the genetic makeup of each shape produced. Each gene represents a unique shape feature for that object and each chromosome a unique object. The chromosomes are used to generate the shapes embodying the classification space. The second algorithm performs a genetic search process until the exemplar shape is generated to match an unknown aircraft. The second algorithm uses the GENEtic Search Implementation System, GENESIS. A basic genetic search algorithm tool, GENESIS employs well known genetic operators of selection, crossover, and mutation to adaptively search the classification space. With each generation, a set of MAT structures result and are input to GENESIS. GENESIS accepts this input and performs requisite computations to yield an improved set of structures. This process continues until the desired shape is established. The object's genetic makeup is determined and can be used to regenerate the object. The chromosome is then compared to that of known aircraft to determine the type of aircraft in question. The procedures and results of utilizing this aircraft classification system on various aircraft silhouettes are presented.