Evolutionary image composition using feature covariance matrices

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.

Evolutionary diversity optimization using multi-objective indicators

“…Random walk lengths are increased in the case of a successful mutation and decreased in the case of unsuccessful ones. For details, we refer the reader to [17,18].…”

Discrepancy-based evolutionary diversity optimization

“…Our new mutation operator enables us to construct diverse sets of images for all three algorithms (including (µ + λ)-EA C investigated in [1]) within just 2000 generations. The random walk in this paper differs from the one for image composition given in [20] by changing the RGB values by an offset vector o ∈ [−r, r] 3 chosen in each mutation step uniformly at random. The mutation operator is shown in the Algorithm 2.…”

Evolution of Images with Diversity and Constraints Using a Generative Adversarial Network

“…Aesthetic feature measures have been often applied to the creation of new artistic images using evolutionary search [3,4,14,16]. There has also been significant work in the evolution of existing images [20,22]. This work differs from previous work in the use of a GAN as a mapper from the latent search vector to the images space and the use of the discriminator network and feature metrics to constrain these images, the space of a generator network as a given image source and use the discriminator and feature metrics to constrain these images.…”