# Evolutionary Image Composition Using Feature Covariance Matrices

## TL;DR

This paper introduces a flexible evolutionary algorithm that creates new images by combining features from existing images using feature covariance matrices, enabling targeted and aesthetically pleasing compositions.

## Contribution

The paper presents a novel evolutionary approach utilizing feature covariance matrices for image composition, allowing flexible feature integration and targeted region editing.

## Key findings

- Generated images are aesthetically pleasing.
- Method effectively targets specific image regions.
- Flexible feature incorporation enhances creative possibilities.

## Abstract

Evolutionary algorithms have recently been used to create a wide range of artistic work. In this paper, we propose a new approach for the composition of new images from existing ones, that retain some salient features of the original images. We introduce evolutionary algorithms that create new images based on a fitness function that incorporates feature covariance matrices associated with different parts of the images. This approach is very flexible in that it can work with a wide range of features and enables targeting specific regions in the images. For the creation of the new images, we propose a population-based evolutionary algorithm with mutation and crossover operators based on random walks. Our experimental results reveal a spectrum of aesthetically pleasing images that can be obtained with the aid of our evolutionary process.