Statistical Image Analysis for Image Evolution

by Elham Salimi
Supervisor: Brian Ross

This research is focused on using genetic programming to evolve images based on lightweight features extracted from a given target image. Research by Lombardi {\em et al.} ("A lightweight image retrieval system for paintings", 2005) propose an image retrieval system that uses a suite of lightweight statistical features of images for comparing and classifying images into painting style categories, primarily based on color matching. In this research, automatic fitness scoring of variations of up to 17 lightweight image features using many-objective fitness evaluation is used to evolve textures. Evolved results were shown to have similar color characteristics to target images.

Downloads

Copyright (c) 2016 Elham Salimi.


Back up: http://www.cosc.brocku.ca/~bross/