Grant: Discovery Grants Program - Individual

Our objective is the development of a prototype of an evolutionary computing platform, which accepts asinput a random sample of images of a certain type, along with their corresponding ground truths. It wouldoutput a computer program that is capable of segmenting unseen images of the same type, with a high degreeof segmentation accuracy and computational efficiency. The platform itself could be described as a geneticprogramming method that evolves a population of feed-forward networks of nodes, corresponding to candidateimage segmentation programs. The particular form of representation is inspired by Cartesian GeneticProgramming (CGP). Each node is defined by its identification number (ID), image transformation,transformation parameters and the IDs of the nodes that provide its input(s). The transformation comes from anopen library of transformations, which include well-known image pre-processing, segmentation andpost-processing methods. The fitness of an individual will be measured from both a pixel-based and aregion-based perspective. The overall evolutionary cycle searches the space of all (small-sized) feed-forwardnetworks, of different structures and parameterizations, for those networks with highest relative fitness values.The ultimate value of our work lies in its attempt to emulate and exceed the manner in which highly-paidprofessionals develop distributed programs for image segmentation. Hence, we would consider our effort asuccess only whence a fully-functional and demonstrable prototype is produced.